The DOI matches its Crossref record; 74 of the 81 references it cites were found in a registry or an index; 2 of the 26 sources its claims cite were checked for support.
Learning Deep CNN Denoiser Prior for Image Restoration
Open accessAbstract
Model-based optimization methods and discriminative learning methods have been the two dominant strategies for solving various inverse problems in low-level vision. Typically, those two kinds of methods have their respective merits and drawbacks, e.g., model-based optimization methods are flexible for handling different inverse problems but are usually time-consuming with sophisticated priors for the purpose of good performance, in the meanwhile, discriminative learning methods have fast testing speed but their application range is greatly restricted by the specialized task. Recent works have revealed that, with the aid of variable splitting techniques, denoiser prior can be plugged in as a modular part of model-based optimization methods to solve other inverse problems (e.g., deblurring). Such an integration induces considerable advantage when the denoiser is obtained via discriminative learning. However, the study of integration with fast discriminative denoiser prior is still lacking. To this end, this paper aims to train a set of fast and effective CNN (convolutional neural network) denoisers and integrate them into model-based optimization method to solve other inverse problems. Experimental results demonstrate that the learned set of denoisers can not only achieve promising Gaussian denoising results but also can be used as prior to deliver good performance for various low-level vision applications.
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
The paper trains a set of fast CNN Gaussian denoisers and uses them as modular priors inside a half-quadratic splitting optimization framework to solve image deblurring and super-resolution. Experiments show competitive denoising accuracy and flexible restoration performance across tasks without task-specific retraining.
Key findings
- The proposed CNN denoiser improves gray-image denoising on BSD68 over BM3D, WNNM, TNRD, and MLP: at σ=15 it reaches 31.63 dB, at σ=25 it reaches 29.15 dB, and at σ=50 it reaches 26.19 dB.
- For color denoising on BSD68, the proposed denoiser consistently beats CBM3D, e.g. 40.36 vs. 40.24 dB at noise level 5, 31.16 vs. 30.71 dB at 25, and 27.86 vs. 27.38 dB at 50.
- The learned denoisers can be inserted into a model-based optimization method to handle deblurring and single-image super-resolution; for example, on the Leaves deblurring case with Gaussian blur σ=1.6 and noise level 2, the proposed method reports 29.78 dB versus 26.95 dB for IDDBM3D and 27.50 dB for NCSR.
- Runtime is competitive: for a 256×256 image with noise level 25, the 24-feature-map version takes 0.10 s on CPU and 0.006 s on GPU, while BM3D takes 0.66 s on CPU and TNRD takes 0.47 s on CPU / 0.010 s on GPU.
Methods
- The authors design a seven-layer CNN denoiser using dilated convolutions with dilation factors 1, 2, 3, 4, 3, 2, 1; middle layers use 64 feature maps, and the effective receptive field is 33×33.
- Training uses 400 BSD images, 400 ImageNet validation images, and 4,744 Waterloo Exploration Database images, cropped into 35×35 patches with N = 256×4,000 patches; Adam is used with residual learning and batch normalization.
- A set of 25 denoisers is trained for gray images and 25 for color images over noise levels from 0 to 50 in steps of 2; these denoisers are integrated into a half-quadratic splitting scheme, where the regularization subproblem becomes a Gaussian denoising step.
Limitations
- The paper states that future work includes reducing the number of CNN denoisers and iterations, extending the framework to inpainting and blind deblurring, and using multiple complementary priors.
- The experimental evaluation is limited to denoising, non-blind deblurring, and super-resolution; inpainting and blind deblurring are not tested.
- The authors note that comparisons with SRCNN and VDSR for non-bicubic super-resolution are unfair because those methods were trained for bicubic degradation, which is evident from the reported setup rather than presented as a limitation of the proposed method.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
2 of 26 cited sources checked · 1 supported · 1 flagged · accuracy not yet measured
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“Note that SRCNN and VDSR are trained with bicubic blur kernel, thus it is unfair to use their models to super-resolve the low-resolution image with Gaussian kernel.”
§ Learning Deep CNN Denoiser Prior for Image Restoration > 4.3. Single Image Super-Resolution
What the sources say
- Disputedcites [21] 21. C. Dong, C. C. Loy, K. He, and X. Tang. Image super-resolution using deep convolutional networks. IEEE transactions on Pattern Analysis and Machine Intelligence, 38(2):295-307, 2016. 2, 7 sourceExperimental — accuracy not yet measured
Section 3.3 (p. 5) says SRCNN training samples are blurred with a Gaussian kernel; bicubic interpolation is a later upscaling step, not the blur kernel. Section 4.4.1 (p. 9) also describes training a separate SRCNN network with a different Gaussian kernel for comparison. The paper does not address VDSR's training. (LLM, conf=0.87)
Checked by a reasoning model — may be wrong.
- Not checked — no full text of the sourcecites [35] 35. J. Kim, J. K. Lee, and K. M. Lee. Accurate image super- resolution using very deep convolutional networks. In IEEE Conference on Computer Vision and Pattern Recognition, pages 1646-1654, 2016. 4, 7 source
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes- Disputed
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Experimental results demonstrate that the learned set of denoisers can not only achieve promising Gaussian denoising results but also can be used as prior to deliver good performance for various low-level vision applications.”
- Also stated in: § 1. Introduction · boosted
“Extensive experiments on classical IR problems, including deblurring and super-resolution, have demonstrated the merits of integrating flexible model-based optimization methods and fast CNN-based discriminative learning methods.”
§ Learning Deep CNN Denoiser Prior for Image Restoration > Abstract
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes- Also stated in: § 1. Introduction · boosted
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“we empirically find it also can enable fast transfer from one model to another with different noise level.”
§ Learning Deep CNN Denoiser Prior for Image Restoration > Using Batch Normalization and Residual Learning to Accelerate Training.
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesThe paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“However, if the size of the training patch is smaller than the receptive field, the performance would decrease.”
§ Learning Deep CNN Denoiser Prior for Image Restoration > Using Batch Normalization and Residual Learning to Accelerate Training.
Strength:hedged· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesA result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“However, the proposed CNN denoiser can have a PSNR gain of about 0.2dB over those three methods.”
§ Learning Deep CNN Denoiser Prior for Image Restoration > 4.1. Image Denoising
Load-bearingStrength:hedged· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesThe paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“We empirically find that using training samples with small size can help avoid boundary artifacts.”
§ Learning Deep CNN Denoiser Prior for Image Restoration > Using Batch Normalization and Residual Learning to Accelerate Training.
Strength:plain· not yet calibratedCausal:conditional· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesA result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We can see that the proposed denoiser is very competitive in both CPU and GPU implementation.”
§ Learning Deep CNN Denoiser Prior for Image Restoration > 4.1. Image Denoising
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesThe paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Due to the iterative scheme, it turns out the noise level range of [0, 50] is enough to handle various image restoration problems.”
§ Learning Deep CNN Denoiser Prior for Image Restoration > Using Batch Normalization and Residual Learning to Accelerate Training.
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes? Based: unclearThe paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“it can be seen that the proposed denoiser consistently outperforms CBM3D by a large margin.”
§ Learning Deep CNN Denoiser Prior for Image Restoration > 4.1. Image Denoising
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesA result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It can be seen that WNNM, MLP and TNRD can outperform BM3D by about 0.3dB in PSNR.”
§ Learning Deep CNN Denoiser Prior for Image Restoration > 4.1. Image Denoising
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes
- It may state two separate claims as one. 13
- Probably not a substantial claim. 10
- The quote only partly states this claim. 1
Every source the paper cites for this claim was checked and supports it.
In the paper
“it has been pointed out that the combination of batch normalization and residual learning is particularly helpful for Gaussian denoising since they are beneficial to each other.”
§ Learning Deep CNN Denoiser Prior for Image Restoration > Using Batch Normalization and Residual Learning to Accelerate Training.
What the sources say
- Supportedcites [65] 65. K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang. Be- yond a Gaussian denoiser: Residual learning of deep CNN for image denoising. IEEE Transactions on Image Process- ing, 2017. 4 source
Section C (pp. 4–5) says residual learning and batch normalization can benefit each other in Gaussian denoising, and reports faster convergence and better denoising performance when combined. Section B (p. 3) also describes their integration as producing fast, stable training and better denoising performance. (LLM, conf=0.95)
Strength:hedged· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
- Supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It is worth emphasizing that the proposed denoiser with 24 feature maps of each layer has a comparable PSNR of 28.94dB to TNRD but delivers a faster speed.”
§ Learning Deep CNN Denoiser Prior for Image Restoration > 4.1. Image Denoising
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
In the paper
“We empirically find using large dataset does not improve the PSNR results of BSD68 dataset [50] but can slightly improve the performance of other testing images.”
§ Learning Deep CNN Denoiser Prior for Image Restoration > 4.1. Image Denoising
What the sources say
- Not checked — no full text of the sourcecites [50] 50. S. Roth and M. J. Black. Fields of experts. International Journal of Computer Vision, 82(2):205-229, 2009. 1, 4, 5 source
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
In the paper
“It turns out that our designed model can have an average P-SNR of 29.15dB on BSD68 dataset [50], which is much better than 28.94dB of 7 layers network with traditional 3×3 convolution filter and very close to 29.20dB of 16 layers network.”
§ Learning Deep CNN Denoiser Prior for Image Restoration > 3.2. The Proposed CNN Denoiser
What the sources say
- Not checked — no full text of the sourcecites [50] 50. S. Roth and M. J. Black. Fields of experts. International Journal of Computer Vision, 82(2):205-229, 2009. 1, 4, 5 source
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As an example for the testing speed comparison, our method can super-resolve the Butterfly image in 0.5 second on GPU and 12 seconds on CPU, whereas NCSR spends 198 seconds on CPU.”
§ Learning Deep CNN Denoiser Prior for Image Restoration > 4.3. Single Image Super-Resolution
Strength:plain· not yet calibratedSingle caseTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
- Rests on an assumption: The low-resolution image can be modeled by a blurring and subsequent down-sampling operation on a high-resolution one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We can see that IDDBM3D, NCSR and MLP tend to smooth the edges and generate color artifacts.”
§ Learning Deep CNN Denoiser Prior for Image Restoration > 4.2. Image Deblurring
Tests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
- The authors state this as an assumption: The convolution is carried out with circular boundary conditions.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“First, although S-RCNN and VDSR achieve promising results to tackle the case with bicubic kernel, their performance deteriorates seriously when the low-resolution image are not generated by bicubic kernel (see Figure 4).”
§ Learning Deep CNN Denoiser Prior for Image Restoration > 4.3. Single Image Super-Resolution
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- Rests on an assumption: The low-resolution image can be modeled by a blurring and subsequent down-sampling operation on a high-resolution one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In contrast, the proposed method can recover image sharpness and naturalness.”
§ Learning Deep CNN Denoiser Prior for Image Restoration > 4.2. Image Deblurring
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- The authors state this as an assumption: The convolution is carried out with circular boundary conditions.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Third, both of the gray and color CNN denoiser prior based optimization methods can produce promising results.”
§ Learning Deep CNN Denoiser Prior for Image Restoration > 4.3. Single Image Super-Resolution
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
- Rests on an assumption: The low-resolution image can be modeled by a blurring and subsequent down-sampling operation on a high-resolution one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Third, CNN exploits the external prior which is complementary to the internal prior of many existing denoisers such as BM3D.”
§ Learning Deep CNN Denoiser Prior for Image Restoration > 3.1. Why Choose CNN Denoiser?
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. The paper may give no reason why it holds.
In the paper
“model-based optimization methods are flexible for handling different inverse problems but are usually time-consuming with sophisticated priors for the purpose of good performance”
- Also stated in: § 1. Introduction · plain
“model-based optimization methods are usually timeconsuming with sophisticated priors for the purpose of good performance [27].”
§ Learning Deep CNN Denoiser Prior for Image Restoration > Abstract
What the sources say
- Not checked — no full text of the sourcecites [27] 27. Q. Gao and S. Roth. How well do filter-based MRFs model natural images? In Joint DAGM (German Association for Pattern Recognition) and OAGM Symposium, pages 62-72, 2012. 2 source
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- Also stated in: § 1. Introduction · plain
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Second, CNN exhibits powerful prior modeling capacity with deep architecture.”
§ Learning Deep CNN Denoiser Prior for Image Restoration > 3.1. Why Choose CNN Denoiser?
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“First, the inference of CNN is very efficient due to the parallel computation ability of GPU.”
§ Learning Deep CNN Denoiser Prior for Image Restoration > 3.1. Why Choose CNN Denoiser?
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Especially noteworthy is the number of the denoisers which is much less than that of learning different models for different degradations.”
§ Learning Deep CNN Denoiser Prior for Image Restoration > Using Batch Normalization and Residual Learning to Accelerate Training.
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✗ Based: failsProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“discriminative learning methods have fast testing speed but their application range is greatly restricted by the specialized task.”
- Also stated in: § 1. Introduction · plain
“discriminative learning methods are usually restricted by specialized tasks.”
§ Learning Deep CNN Denoiser Prior for Image Restoration > Abstract
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- Also stated in: § 1. Introduction · plain
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Such a good compromise between speed and performance over TNRD is properly attributed to the following three reasons.”
§ Learning Deep CNN Denoiser Prior for Image Restoration > 4.1. Image Denoising
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one. The quote only partly states this claim.
In the paper
“and it is preferable to jointly handle RGB channels.”
§ Learning Deep CNN Denoiser Prior for Image Restoration > 3.1. Why Choose CNN Denoiser?
What the sources say
- Not matchedcites [42] 42. T. Miyata. Inter-channel relation based vectorial total varia- tion for color image recovery. In IEEE International Confer- ence on Image Processing,, pages 2251-2255, 2015. 3
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim.
- Not matched
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“To make a further comparison with TNRD under similar PSNR performance, we additionally provide the run time of the proposed denoiser where each middle layer has 24 feature maps.”
§ Learning Deep CNN Denoiser Prior for Image Restoration > 4.1. Image Denoising
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“the denoiser here just acts its own role regardless of the noise type and noise level of the image to be denoised.”
§ Learning Deep CNN Denoiser Prior for Image Restoration > Using Batch Normalization and Residual Learning to Accelerate Training.
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. The paper may give no reason why it holds.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“To show the advantage of our design over the above two cases, we have trained three different models on noise level 25 with same training settings.”
§ Learning Deep CNN Denoiser Prior for Image Restoration > 3.2. The Proposed CNN Denoiser
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“It is worthy noting that the iterative regularization step of methods such as NCSR and WNNM actually corresponds to solving Eqn.(6a).”
§ Learning Deep CNN Denoiser Prior for Image Restoration > 4.3. Single Image Super-Resolution
Strength:plain· not yet calibratedCausal:correlational· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✗ Based: failsProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“The number of iterations is set to 30 as we find it is large enough to obtain a satisfying performance.”
§ Learning Deep CNN Denoiser Prior for Image Restoration > 4.2. Image Deblurring
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✗ Based: failsProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
- The authors state this as an assumption: The convolution is carried out with circular boundary conditions.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“On the other hand, different from discriminative learning methods which are specialized for certain image restoration tasks, the proposed deep CNN denoiser prior based optimization method is flexible in handling various tasks while can produce very favorable results.”
§ Learning Deep CNN Denoiser Prior for Image Restoration > 5. Conclusion
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The paper relies on this without support.
The study of integration with fast discriminative denoiser prior is still lacking.
“However, the study of integration with fast discriminative denoiser prior is still lacking.”
“However, to the best of our knowledge, the study of integration with discriminative denoiser is still lacking.”
The authors state this as an assumption.
The convolution is carried out with circular boundary conditions.
“In addition, we assume the convolution is carried out with circular boundary conditions.”
The paper relies on this without support.
The low-resolution image can be modeled by a blurring and subsequent down-sampling operation on a high-resolution one.
“In general, the low-resolution (LR) image can be modeled by a blurring and subsequent down-sampling operation on a high-resolution one.”
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1×
“Thus, using 3×3 filter with a large depth is popularized in existing CNN network design [30, 35, 56].”
MethodVery Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 1×
“However, increasing the filter size would not only introduce more parameters but also increase the computational burden [53].”
BackgroundImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 1×
“Particularly, several CNN techniques, including Rectifier Linear Units (ReLU) [37], batch normalization [32], Adam [36], dilated convolution [63] are adopted into the network design or training.”
MethodAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 5×
“Particularly, several CNN techniques, including Rectifier Linear Units (ReLU) [37], batch normalization [32], Adam [36], dilated convolution [63] are adopted into the network design or training.”
MethodInfluentialImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 1×
“Hence, instead of training on a small dataset consisting of 400 Berkeley segmentation dataset (BSD) images of size 180×180 [13], we collect a large dataset which includes 400 BSD images, 400 selected images from validation set of ImageNet database [20] and 4,744 images of Waterloo Exploration Database [40].”
MethodGoing deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562 · cited 1×
“Thus, using 3×3 filter with a large depth is popularized in existing CNN network design [30, 35, 56].”
MethodBatch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818 · cited 2×
“Particularly, several CNN techniques, including Rectifier Linear Units (ReLU) [37], batch normalization [32], Adam [36], dilated convolution [63] are adopted into the network design or training.”
BackgroundMethodBoyd, S., Parikh, N., Chu, E., Peleato, B., & Eckstein, J. (2011) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000016 · Cited by 17,075
Boyd, S. (2010) · now publishers, Inc. eBooks · doi:10.1561/9781601984616 · Cited by 12,917
A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
Beck, A., & Teboulle, M. (2009) · SIAM Journal on Imaging Sciences · doi:10.1137/080716542 · Cited by 11,952 · cited 1×
“Note that this property can be also employed in other optimization methods ( e.g ., iterative shrink-age/thresholding algorithms ISTA [4, 14] and FISTA [3]) as long as there involves a denoising subproblem.”
Flagged first, then by citations
6 of the 81 references couldn’t be matched to a known paper.
Research works printed but not linked: 2
- foi, 2006, Pointwise shape adaptive DCT denoising with structure preservation in luminance-chrominance space, International Workshop on Video Processing and Quality Metrics for Consumer Electronics
- danielyan, 2010, Image deblurring by augmented lagrangian with BM3D frame prior, Workshop on Information Theoretic Methods in Science and Engineering, 16
Cited by
Sorted by citations
Image Super-Resolution Using Very Deep Residual Channel Attention Networks
Zhang, Y., Li, K., Li, K., Wang, L., Zhong, B., & Fu, Y. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01234-2_18 · Cited by 6,003
“We further apply our method to super-resolve images with blur-down (BD) degradation model, which is also commonly used recently [11,15,17].”
BackgroundMethodInfluentialSwinIR: Image Restoration Using Swin Transformer
Liang, J., Cao, J., Sun, G., Zhang, K., Gool, L. V., & Timofte, R. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00210 · Cited by 5,150
“Dataset σ BM3D [14] DnCNN [90] IRCNN [91] FFDNet [92] DSNet [64] RPCNN [85] BRDNet [71] RNAN [96] RDN [98] IPT [9] DRUNet [88] SwinIR (ours)”
BackgroundMethodInfluentialSelf-citationResidual Dense Network for Image Super-Resolution
Zhang, Y., Tian, Y., Kong, Y., Zhong, B., & Fu, Y. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00262 · Cited by 4,371
“Our RDN is compared with SPMSR [20], SRCNN [3], FSRCNN [4], VDSR [10], IRCNN G [38], and IRCNN C [38].”
BackgroundMethodResultInfluentialRestormer: Efficient Transformer for High-Resolution Image Restoration
Zamir, S. W., Arora, A., Khan, S., Hayat, M., Khan, F. S., & Yang, M. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00564 · Cited by 4,737
FFDNet: Toward a Fast and Flexible Solution for CNN-Based Image Denoising
Zhang, K., Zuo, W., & Zhang, L. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2839891 · Cited by 2,990
“In [9], dilated convolution is introduced to expand receptive field without the increase of network depth, resulting in a 7-layer denoising CNN.”
BackgroundInfluentialSelf-citationPre-Trained Image Processing Transformer
Chen, H., Wang, Y., Guo, T., Xu, C., Deng, Y., Liu, Z., Ma, S., Xu, C., Xu, C., & Gao, W. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01212 · Cited by 2,308
“…of the proposed method, Urban100( × 4): img 004 HR VDSR[41] EDSR[51] RDN[94] OISR[35] SAN[17] RNAN [93] IGNN BSD68: 163085 GT Noisy ( σ =50) CBM3D [16] TNRD [14] RDN [94] DnCNN [87] MemNet [65] IRCNN [88] FFDNet [89] IPT (ours) we compare our results with various state-of-the-art models.”
ResultMulti-Stage Progressive Image Restoration
Zamir, S. W., Arora, A., Khan, S. H., Hayat, M., Khan, F. S., Yang, M., & Shao, L. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.01458 · Cited by 2,303
“To ameliorate this issue, recent state-of-the-art approaches [17, 44, 57, 86, 87, 93, 94, 97] employ convolutional neural networks (CNNs) that im-”
BackgroundSecond-Order Attention Network for Single Image Super-Resolution
Dai, T., Cai, J., Zhang, Y., Xia, S.-T., & Zhang, L. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01132 · Cited by 2,010
“We compare our method with 8 state-of-the-art SR methods: SPMSR [24], SRCNN [2], FSRCNN [3], VDSR [12], IR-CNN [35], SRMD [36], RDN [39], and RCAN [38].”
MethodDeep Learning for Image Super-Resolution: A Survey
Wang, Z., Chen, J., & Hoi, S. C. H. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2982166 · Cited by 2,113
“[107] replace the common convolution by dilated convolution in SR models, increase the receptive field over twice and achieve much better performance.”
BackgroundISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing
Zhang, J., & Ghanem, B. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00196 · Cited by 1,438
“From Table 1, we observe that SDA and ReconNet work better at 1We use the source code made publicly available by the authors of TVAL3 [22], D-AMP [28], IRCNN [49], and ReconNet [21] and implement SDA [30] ourselves, since its source code is not available. extremely low CS ratios of 1% and 4%, while traditional optimiz…”
MethodInfluentialDeep Learning for Single Image Super-Resolution: A Brief Review
Yang, W., Zhang, X., Tian, Y., Wang, W., Xue, J., & Liao, Q. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2919431 · Cited by 1,202
Learning a Single Convolutional Super-Resolution Network for Multiple Degradations
Zhang, K., Zuo, W., & Zhang, L. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00344 · Cited by 1,174
“For example, the method proposed in [57] can handle the widelyused Gaussian degradation as in [11].”
BackgroundMethodInfluentialSelf-citationPlug-and-Play Image Restoration With Deep Denoiser Prior
Zhang, K., Li, Y., Zuo, W., Lei Zhang, A., Gool, L. V., & Timofte, R. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3088914 · Cited by 1,152
“For example, the IR-CNN [17] denoisers involve 25 separate 7-layer denoisers, each of which is trained on an interval noise level of 2.”
BackgroundMethodInfluentialSelf-citationMoDL: Model-Based Deep Learning Architecture for Inverse Problems
Aggarwal, H. K., Mani, M., & Jacob, M. (2018) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2018.2865356 · Cited by 1,210
FFDNet: Toward a fast and flexible solution for CNN-Based image denoising
Zhang, K., Zuo, W., & Zhang, L. (2018) · TUScholarShare (Temple University) · Cited by 916
Self-citationMulti-level Wavelet-CNN for Image Restoration
Liu, P., Zhang, H., Zhang, K., Lin, L., & Zuo, W. (2018) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2018.00121 · Cited by 998
“By incorporating with unrolled inference, any restoration tasks can be tackled by sequentially applying the CNN denoisers [58].”
BackgroundMethodInfluentialSelf-citationResidual Dense Network for Image Restoration
Zhang, Y., Tian, Y., Kong, Y., Zhong, B., & Fu, Y. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2968521 · Cited by 904
Feedback Network for Image Super-Resolution
Li, Z., Yang, J., Liu, Z., Yang, X., Jeon, G., & Wu, W. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00399 · Cited by 934
“Dataset Model Bicubic SRCNN VDSR IRCNN G IRCNN C SRMD(NF) RDN SRFBN SRFBN+ [7] [18] [43] [43] [44] [47] (Ours) (Ours) Set5 BD 28.”
BackgroundMethodDesigning a Practical Degradation Model for Deep Blind Image Super-Resolution
Zhang, K., Liang, J., Gool, L. V., & Timofte, R. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00475 · Cited by 867
“As mentioned in the introduction, existing DNNs-based SISR methods are generally based on bicubic downsam-pling [23, 44] and traditional degradations [26, 37, 54, 59, 60], or some simple variants [11, 41, 53, 56, 58].”
BackgroundMethodSelf-citationReal Image Denoising With Feature Attention
Anwar, S., & Barnes, N. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00325 · Cited by 784
“NLNet improved upon the traditional methods; but, it lags in performance compared to most of the CNNs [64, 63] due to the adaptaton of NSS priors, as it is unable to find the analogs for all the patches in the image.”
BackgroundMethodInfluentialSingle Image Super-Resolution via a Holistic Attention Network
Niu, B., Wen, W., Ren, W., Zhang, X., Yang, L., Wang, S., Zhang, K., Cao, X., & Shen, H. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58610-2_12 · Cited by 862
“We compare the proposed method with nine state-of-the-art super-resolution methods: SPMSR [25], SRCNN [3], FSRCNN [4], VDSR [15], IRCNN [37], SRMD [39], RDN [41], RCAN [40],SRFBN [21] and SAN [2].”
MethodSelf-citationAttention-guided CNN for image denoising
Tian, C., Xu, Y., Li, Z., Zuo, W., Fei, L., & Liu, H. (2020) · Neural Networks · doi:10.1016/j.neunet.2019.12.024 · Cited by 688
“Images C.man House Peppers Starfish Monarch Airplane Parrot Lena Barbara Boat Man Couple Average Noise Level σ = 15 BM3D [8] 31.91 34.93 32.69 31.14 31.85 31.07 31.37 34.26 33.10 32.13 31.92 32.10 32.37 WNNM [13] 32.17 35.13 32.99 31.82 32.71 31.39 31.62 34.27 33.60 32.27 32.11 32.17 32.70 EPLL [64] 31.85 34.17 32.64…”
MethodInfluentialSelf-citationDeep Unfolding Network for Image Super-Resolution
Zhang, K., Gool, L. V., & Timofte, R. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00328 · Cited by 689
“The compared methods include RCAN [70], ZSSR [51], IKC [20] and IRCNN [65].”
BackgroundMethodResultSelf-citationConvolutional Neural Networks for Inverse Problems in Imaging: A Review
McCann, M. T., Jin, K. H., & Unser, M. A. (2017) · IEEE Signal Processing Magazine · doi:10.1109/msp.2017.2739299 · Cited by 794
“Recent work has made progress in the direction by learning a CNN-based proximal operator which can be used inside an iterative optimization method for any inverse problem [32]*. 3) Multidimensional Signals: Modern inverse problems in imaging increasing involve reconstruction of 3D or 3D+time images.”
MethodImage Blind Denoising with Generative Adversarial Network Based Noise Modeling
Chen, J., Chen, J., Chao, H., & Yang, M. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00333 · Cited by 627
“These approaches [3, 30, 31], especially those based on Convolutional Neural Network (CNN) [33, 16, 32], train a deep denoising network with paired training datasets and learn the underlying noise model implicitly, which obtains remarkable results.”
BackgroundResidual Feature Aggregation Network for Image Super-Resolution
Liu, J., Zhang, W., Tang, Y., Tang, J., & Wu, G. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00243 · Cited by 652
“We compare our RFANet with 10 state-of-the-art methods: SPMSR [22], SRCNN [4], FSRCNN [5], VDSR [13], IRCNN [35], SRMD [36], RDN [40], SRFBN [17], RCAN [38], and SAN [ 3].”
MethodMambaIR: A Simple Baseline for Image Restoration with State-Space Model
Guo, H., Li, J., Dai, T., Ouyang, Z., Ren, X., & Xia, S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72649-1_13 · Cited by 738
Using Deep Neural Networks for Inverse Problems in Imaging: Beyond Analytical Methods
Lucas, A. M., Iliadis, M., Molina, R., & Katsaggelos, A. K. (2018) · IEEE Signal Processing Magazine · doi:10.1109/msp.2017.2760358 · Cited by 584
“[52] (2017) Denoising, inpainting, and SR Ten-layer encoder-decoder CNN for projection operator in the alternating direction method of multipliers (ADMM) method; residual blocks; adversarial training”
MethodImage denoising using deep CNN with batch renormalization
Tian, C., Xu, Y. D., & Zuo, W. (2019) · Neural Networks · doi:10.1016/j.neunet.2019.08.022 · Cited by 594
“A good denoiser should realize a tradeoff between PSNR and running time [62].”
BackgroundMethodInfluentialSelf-citationDeep Learning Techniques for Inverse Problems in Imaging
Ongie, G., Jalal, A., Metzler, C. A., Baraniuk, R. G., Dimakis, A. G., & Willett, R. M. (2020) · IEEE Journal on Selected Areas in Information Theory · doi:10.1109/jsait.2020.2991563 · Cited by 647
“ting [105], [106], block coordinate descent [107]–[109], alternating minimization [82], and approximate message passing [88], [110].”
BackgroundMethodDeep Learning for Geophysics: Current and Future Trends
Yu, S., & Ma, J. (2021) · Reviews of Geophysics · doi:10.1029/2021rg000742 · Cited by 603
Chen, K., Pu, X., Ren, Y., Qiu, H., Lin, F., & Zhang, S. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3034752 · Cited by 584
Denoising Prior Driven Deep Neural Network for Image Restoration
Dong, W., Wang, P., Yin, W., Shi, G., Wu, F., & Lu, X. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2873610 · Cited by 530
“For this case, we compare the proposed method with DD-CNN [36], which has much better results than their earlier DnCNN [24].”
BackgroundMethodInfluentialYuan, Q., Zhang, Q., Li, J., Shen, H., & Zhang, L. (2018) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2018.2865197 · Cited by 540
“Furthermore, another possible strategy which will be explored in our subsequent research will be to add a priori constraint or structure (such as graph regularization [46], minimal hashing [47], encoderdecoder network [48], and ADMM denoiser [49]) to the deep CNNs to reduce the spectral distortion and improve the text…”
BackgroundSelf-citationLearning to Restore Low-Light Images via Decomposition-and-Enhancement
Xu, K., Yang, X. S., Yin, B., & Lau, R. W. H. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00235 · Cited by 484
“Deep learning has also been widely applied to the denoising problem [33, 49, 50, 27, 37, 32].”
BackgroundMethodAll-In-One Image Restoration for Unknown Corruption
Li, B., Liu, X., Hu, P., Wu, Z., Lv, J., & Peng, X. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01693 · Cited by 467
“Method CBM3D [5] DnCNN [53] IRCNN [54] FFDNet [55] BRDNet [40] DL [8] Ours”
MethodDeep Plug-And-Play Super-Resolution for Arbitrary Blur Kernels
Zhang, K., Zuo, W., & Lei Zhang, A. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00177 · Cited by 417
“[63] proposed a plug-and-play framework (IRCNN) to solve the energy function induced by Eqn.”
BackgroundMethodSelf-citationA Deep Journey into Super-resolution
Anwar, S., Khan, S. H., & Barnes, N. M. (2020) · ACM Computing Surveys · doi:10.1145/3390462 · Cited by 505
“The architecture of SRMD is similar to [28], [30], [31].”
BackgroundResultInfluentialDeep Image Deblurring: A Survey
Zhang, K., Ren, W., Luo, W., Lai, W., Stenger, B., Yang, M., & Li, H. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01633-5 · Cited by 436
Self-citationXiao, J., Fu, X., Liu, A., Wu, F. H., & Zha, Z.-J. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3183612 · Cited by 420
“In recent years, deep learning are widely used in various image processing tasks [17], [18], [31], [32], [33], [34], [35], such as de-noising [36], [37], [38], super-resolution [39], [40], [41], de-blurring [42], [43], [44], [45], de-hazing [19], [19], [46], [47], [48], [49], [50], low-light image…”
NTIRE 2018 Challenge on Single Image Super-Resolution: Methods and Results
Timofte, R., Gu, S., Wu, J., Gool, L. V., Lei Zhang, A., Yan, S., Haris, M., Shakhnarovich, G., Ukita, N., Hu, S., et al. (2018) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2018.00130 · Cited by 341
“Second, for IRMem, the authors design a memory block with an IRCNN [41] block, which delete all the BN layer and add residual factor assigned 0.1, and embeded this memory block into EDSR [21].”
MethodInfluentialSelf-citationShlezinger, N., Whang, J., Eldar, Y. C., & Dimakis, A. G. (2023) · Proceedings of the IEEE · doi:10.1109/jproc.2023.3247480 · Cited by 470
Single Image Deraining: A Comprehensive Benchmark Analysis
Li, S., Araujo, I. B., Ren, W., Wang, Z., Tokuda, E. K., Hirata, R., Cesar-Junior, R., Zhang, J., Guo, X., & Cao, X. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00396 · Cited by 361
“Data-driven CNN models: Recently, CNNs have achieved dominant success for image restoration [28, 29] including single image deraining [30, 31].”
BackgroundPointCleanNet : Learning to Denoise and Remove Outliers from Dense Point Clouds
Rakotosaona, M., Barbera, V. L., Guerrero, P., Mitra, N. J., & Ovsjanikov, M. (2019) · Computer Graphics Forum · doi:10.1111/cgf.13753 · Cited by 381
“More recently, to address the limitations mentioned above, and inspired by the success of deep learning for other tasks, several learning-based denoising methods have also been proposed for both images [ZZC ∗ 17, ZZGZ17, JMFU17] and more recently meshes [WLT16, BBZ ∗ 18], among others.”
BackgroundProximal Dehaze-Net: A Prior Learning-Based Deep Network for Single Image Dehazing
Yang, D., & Sun, J. Z. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01234-2_43 · Cited by 322
“2 Learning CNNs for image inverse problems Recently, there have been several works to solve image inverse problems in deep learning frameworks [17, 22, 33, 35, 36].”
BackgroundNeural Blind Deconvolution Using Deep Priors
Ren, D., Zhang, K., Wang, Q., Hu, Q., & Zuo, W. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00340 · Cited by 337
“Thus, the priors should favor natural images, e.g ., hyper-Laplacian [14], GMM [55], non-local similarity [5], e.g ., RTF [37], CSF [36] and CN-N [16,53], which are quite different from those used in blur kernel estimation.”
BackgroundSelf-citationMulti-Level Wavelet Convolutional Neural Networks
Liu, P., Zhang, H., Lian, W., & Zuo, W. (2019) · IEEE Access · doi:10.1109/access.2019.2921451 · Cited by 347
“Thus, any restoration tasks can be tackled by sequentially applying the CNN denoisers via incorporating with unrolled inference [12].”
BackgroundMethodInfluentialSelf-citationFISTA-Net: Learning a Fast Iterative Shrinkage Thresholding Network for Inverse Problems in Imaging
Xiang, J., Dong, Y., & Yang, Y. (2021) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2021.3054167 · Cited by 329
Universal Denoising Networks : A Novel CNN Architecture for Image Denoising
Lefkimmiatis, S. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00338 · Cited by 310
“Despite these beliefs, very recently and thanks to the advent of deep learning techniques, several powerful image denoising algorithms that managed to significantly improve the state-of-the-art performance have been introduced [6, 23, 38, 40, 42, 43].”
BackgroundDiving deeper into underwater image enhancement: A survey
Anwar, S., & Li, C. (2020) · Signal Processing Image Communication · doi:10.1016/j.image.2020.115978 · Cited by 342
“oved the performance of high-level vision tasks such as object detection [47] and object recognition [19]. Moreover, the low-level vision tasks, such as image superresolution [15] and image denoising [65], also benet from the advantages of deep networks and deliver stateof-the-art performance. Unfortunately, we are un…”
BackgroundAMP-Net: Denoising-Based Deep Unfolding for Compressive Image Sensing
Zhang, Z., Liu, Y., Liu, J., Wen, F., & Zhu, C. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3044472 · Cited by 334
Image super-resolution: A comprehensive review, recent trends, challenges and applications
Lepcha, D. C., Goyal, B., Dogra, A., & Goyal, V. (2022) · Information Fusion · doi:10.1016/j.inffus.2022.10.007 · Cited by 342
Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
Pan, X., Zhan, X., Dai, B., Lin, D., Loy, C. C., & Luo, P. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3115428 · Cited by 312
“ors developed for low-level restoration tasks like deep denoiser prior [42,6] and TNRD [8], but competing with them is not our goal.”
BackgroundDeep Generalized Unfolding Networks for Image Restoration
Mou, C., Wang, Q., & Zhang, J. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01688 · Cited by 315
“Such correspondence was originally applied in deep plugand-play (PNP) methods [44, 57, 74, 92, 94], which utilize trained denoiser to implicitly express the regularization term J(x) as a denoising problem.”
MethodDensely Residual Laplacian Super-Resolution
Anwar, S., & Barnes, N. M. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3021088 · Cited by 293
“We compare against super-resolving noisy image algorithms, which include (SRNI) [55], BM3D-SR [54] and NLM-SR [56] as well as the image restoration algorithm IRCNN [21].”
BackgroundMethodResultInfluentialDeepISP: Toward Learning an End-to-End Image Processing Pipeline
Schwartz, E., Giryes, R., & Bronstein, A. M. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2872858 · Cited by 266
Effects of Image Degradation and Degradation Removal to CNN-Based Image Classification
Pei, Y., Huang, Y., Zou, Q., Zhang, X., & Wang, S. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2950923 · Cited by 285
“For the research on images with white Gaussian noise , Kai et al. [59] trained a set of fast and effective CNN denoisers and integrated them into model-based optimization for solving inverse problems.”
MethodHallucinated-IQA: No-Reference Image Quality Assessment via Adversarial Learning
Lin, K.-Y., & Wang, G. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00083 · Cited by 284
“IQA serves as a key component in the low-level computer vision community and has a wide range of applications [13, 26, 49].”
BackgroundModel-Guided Deep Hyperspectral Image Super-Resolution
Dong, W., Zhou, C., Wu, F., Wu, J., Shi, G., & Li, X. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3078058 · Cited by 258
“although the unfolding strategy has been successfully used for the restoration of natural images [45], [46], [49], similar success has not been witnessed for HSISR yet [10], [13].”
MethodA robust deformed convolutional neural network (CNN) for image denoising
Zhang, Q., Xiao, J., Tian, C., Lin, J. C., & Zhang, S. (2022) · CAAI Transactions on Intelligence Technology · doi:10.1049/cit2.12110 · Cited by 251
Kamilov, U. S., Bouman, C. A., Buzzard, G. T., & Wohlberg, B. E. (2023) · IEEE Signal Processing Magazine · doi:10.1109/msp.2022.3199595 · Cited by 248
“Work related to the use of CNNs as priors includes [37], which describes certain empirical advantages enjoyed by CNN denoisers; [38], which uses CNN denoisers with (F)ISTA on a modified cost function with convergence/accuracy benefits [39]; and [40], which is related to RED with a motivation that comes from an analysi…”
Double image encryption algorithm based on neural network and chaos
Man, Z., Li, J., Di, X., Sheng, Y., & Liu, Z. (2021) · Chaos, Solitons & Fractals · doi:10.1016/j.chaos.2021.111318 · Cited by 241
Deep Learning for Industrial Computer Vision Quality Control in the Printing Industry 4.0
Villalba-Díez, J., Schmidt, D., Gevers, R., Ordieres-Meré, J. B., Buchwitz, M., & Wellbrock, W. (2019) · Sensors · doi:10.3390/s19183987 · Cited by 260
“It was decided not to use specific denoising treatments as specific filters before classification [38,39].”
MethodBringing Old Photos Back to Life
Wan, Z., Zhang, B., Chen, D., Zhang, P., Chen, D., Liao, J., & Wen, F. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00282 · Cited by 252
“With the emergence of deep learning, one can address a variety of low-level image restoration problems [5, 6, 7, 8, 9, 10, 11, 12] by exploiting the powerful representation capability of convolutional neural networks, i.e ., learning the mapping for a specific task from a large amount of synthetic…”
Optimization-Inspired Compact Deep Compressive Sensing
Zhang, J., Zhao, C., & Gao, W. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.2977507 · Cited by 239
“Quite recently some fast and effective convolutional neural network (CNN) denoisers are trained and integrated into Half Quadratic Splitting (HQA) [30] and alternating direction method of multipliers (ADMM) [31], [32] to solve image inverse problems.”
MethodDeep Gradient Projection Networks for Pan-sharpening
Xu, S., Zhang, J., Zhao, Z., Sun, K., Liu, J., & Zhang, C. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00142 · Cited by 247
NBNet: Noise Basis Learning for Image Denoising with Subspace Projection
Cheng, S., Wang, Y., Huang, H., Liu, D., Fan, H., & Liu, S. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00486 · Cited by 253
“Later on, More network structures were proposed to either enlarge the receptive field or balance the efficiency, like dilated convolution [51], autoencoder with skip connection [30], ResNet [35], recursively branched deconvolutional network (RBDN) [38].”
BackgroundWhen Image Denoising Meets High-Level Vision Tasks: A Deep Learning Approach
Liu, D., Wen, B., Liu, X., Wang, Z., & Huang, T. S. (2018) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/117 · Cited by 240
“A visual comparison is illustrated for a zoomin region: (II) and (III) are the denoising results using CBM3D [Dabov et al., 2007a], and DnCNN [Zhang et al., 2017a], respectively; (IV) is the proposed denoiser trained separately without the guidance of high-level vision information; (V) is the…”
BackgroundMethodResultInfluentialImage Restoration by Iterative Denoising and Backward Projections
Tirer, T., & Giryes, R. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2875569 · Cited by 214
“2 We compare the IDBP performance to P&P and to the recent state-of-the-art method IRCNN [22].”
Transfer Learning From Synthetic to Real-Noise Denoising With Adaptive Instance Normalization
Kim, Y., Soh, J. W., Park, G. Y., & Cho, N. I. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00354 · Cited by 232
“The CNNs trained with RN datasets robustly work on the real-world images, because domains of training and test set almost coincide.”
BackgroundMethodInfluentialDenoising Diffusion Models for Plug-and-Play Image Restoration
Zhu, Y., Zhang, K., Liang, J., Cao, J., Wen, B., Timofte, R., & Gool, L. V. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00129 · Cited by 294
“[58] made the first attempt to incorporate deep denoiser priors to solve various IR tasks.”
BackgroundSelf-citationReplacing Mobile Camera ISP with a Single Deep Learning Model
Ignatov, A., Gool, L. V., & Timofte, R. (2020) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00276 · Cited by 226
“Image deblurring [6, 48, 38, 51] and denoising [65, 64, 66, 52] are the other two related tasks targeted at removing blur and noise from the pictures.”
BackgroundDesigning and training of a dual CNN for image denoising
Tian, C., Xu, Y. D., Zuo, W., Du, B., Lin, C., & Zhang, D. D. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.106949 · Cited by 228
“86 IRCNN [16] 32.”
BackgroundMethodSelf-citationAn Online Plug-and-Play Algorithm for Regularized Image Reconstruction
Sun, Y., Wohlberg, B. E., & Kamilov, U. S. (2019) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2019.2893568 · Cited by 202
Omni Aggregation Networks for Lightweight Image Super-Resolution
Wang, H., Chen, X., Ni, B., Liu, Y., & Liu, J. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.02143 · Cited by 234
“LR images are generated by bicubic downsampling [63] from HR images.”
MethodA Residual Dense U-Net Neural Network for Image Denoising
Gurrola-Ramos, J., Dalmau, O., & Alarcón, T. E. (2021) · IEEE Access · doi:10.1109/access.2021.3061062 · Cited by 209
“We compare our proposed RDUNet model with BM3D [2], [35], DnCNN [15], FFDNet [18], IRCNN [36], RDN [21], DHDN [5], DIDN [6].”
MethodConnecting Image Denoising and High-Level Vision Tasks via Deep Learning
Liu, D., Wen, B., Jiao, J., Liu, X., Wang, Z., & Huang, T. S. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2964518 · Cited by 203
Non-local Meets Global: An Integrated Paradigm for Hyperspectral Image Restoration
He, W. P., Yao, Q., Li, C., Yokoya, N., Zhao, Q., Zhang, H., & Zhang, L. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3027563 · Cited by 258
“Inspired by the success of halfquadratic splitting in image processing [66], [69], we introduce an auxiliary variable Z and propose to relax (4) as follows:”
BackgroundMethodSelf-citationLearning Event-Based Motion Deblurring
Jiang, Z., Zhang, Y., Zou, D., Ren, J., Lv, J., & Liu, Y. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00338 · Cited by 204
“Instead of using simple image prior, we borrow from recent research on learning deep denoising prior [53, 50].”
MethodRestormer: Efficient Transformer for High-Resolution Image RestorationPreprint
Zamir, S. W., Arora, A., Khan, S. H., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.09881 · Cited by 194
Non-Local Meets Global: An Integrated Paradigm for Hyperspectral Denoising
He, W. P., Yao, Q., Li, C., Yokoya, N., & Zhao, Q. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00703 · Cited by 199
“In future, we plan to adopt Convolu-tional Neural Network [8, 47, 45] to explore non-local similarity; and automated machine learning [42] to help tuning and configuring hyper-parameters.”
MethodDual residual attention network for image denoising
Wu, W., Liu, S., Xia, Y., & Zhang, Y. (2024) · Pattern Recognition · doi:10.1016/j.patcog.2024.110291 · Cited by 205
Hyperspectral Image Reconstruction Using a Deep Spatial-Spectral Prior
Wang, L., Sun, C., Fu, Y., Kim, M. H., & Huang, H. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00822 · Cited by 201
“A similar approach has been exploited for natural image restoration, where deep image priors are adopted as regularizers in the optimization [24].”
BackgroundMethodCompact snapshot hyperspectral imaging with diffracted rotation
Jeon, D. S., Baek, S., Yi, S., et al. (2019) · ACM Transactions on Graphics · doi:10.1145/3306346.3322946 · Cited by 185
“Recently, state-of-the-art optimization-based unrolled network architectures [Dong et al. 2018; Wang et al. 2019; Zhang and Ghanem 2018; Zhang et al. 2017] were proposed by adopting, for instance, the traditional ADMM and ISTA methods in a neural network form, and they outperform existing methods for image restoration.”
MethodImage Restoration Using Total Variation Regularized Deep Image Prior
Liu, J., Sun, Y., Xu, X., & Kamilov, U. S. (2019) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2019.8682856 · Cited by 213
“As a baseline, we compared our method with IRCNN [12] and DIP itself based on the same set of images in denoising.”
MethodKernel Modeling Super-Resolution on Real Low-Resolution Images
Zhou, R., & Susstrunk, S. E. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00252 · Cited by 170
“Recent methods do propose to incorporate the degradation parameters including the blur-kernel into the network [14, 43, 51, 52, 53].”
MethodBlind Image Super-Resolution: A Survey and Beyond
Liu, A., Liu, Y., Gu, J., Qiao, Y., & Dong, C. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3203009 · Cited by 200
Image denoising using complex-valued deep CNN
Quan, Y., Chen, Y., Shao, Y., Teng, H., Xu, Y., & Ji, H. (2020) · Pattern Recognition · doi:10.1016/j.patcog.2020.107639 · Cited by 185
“It is not only of practical importance with the prevalence of photography using mobile devices, but also serves as a key component in most image recovery tasks; see e.g. [ 1, 2].”
BackgroundMethodNeumann Networks for Linear Inverse Problems in Imaging
Gilton, D., Ongie, G., & Willett, R. M. (2019) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2019.2948732 · Cited by 193
“More recent work has illustrated the efficacy of unrolled optimization as applied to (proximal) gradient descent [33], [38], [39], alternating directions method of multipliers [40], primal-dual methods [41], half-quadratic splitting [42], [43], block coordinate descent [44]–[46], alternating minimization [47], iterati…”
MethodEnhanced CNN for image denoising
Tian, C., Xu, Y. D., Fei, L., Wang, J., Wen, J., & Luo, N. (2019) · CAAI Transactions on Intelligence Technology · doi:10.1049/trit.2018.1054 · Cited by 176
Dense Deconvolutional Network for Skin Lesion Segmentation
Li, H., He, X., Zhou, F., Yu, Z. X., Ni, D., Chen, S., Wang, T., & Lei, B. (2018) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2018.2859898 · Cited by 168
“Hence, many studies have adopted the dilated convolution [18], [45], [46], which can keep the original resolution and increase the”
BackgroundSwin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration
Conde, M. V., Choi, U.-J., Burchi, M., & Timofte, R. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-25063-7_42 · Cited by 186
Deep Iterative Down-Up CNN for Image Denoising
Yu, S., Park, B., & Jeong, J. (2019) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2019.00262 · Cited by 173
“Zhang et al. [13] proposed a CNN with seven layers, considering the trade - off between computational cost and accuracy.”
BackgroundMethodCOAST: COntrollable Arbitrary-Sampling NeTwork for Compressive Sensing
You, D., Zhang, J., Xie, J., Chen, B., & Ma, S. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3091834 · Cited by 172
“Recently, some fast and effective convolutional neural network (CNN) denoisers are trained and integrated into Half Quadratic Splitting (HQS) [34] and alternating direction method of multipliers (ADMM) [35], [36] to solve image inverse problems.”
A comprehensive review of deep learning-based single image super-resolution
Bashir, S. M. A., Wang, Y., Khan, M., & Niu, Y. (2021) · PeerJ Computer Science · doi:10.7717/peerj-cs.621 · Cited by 185
“In dilated convolution, the contextual information is used to generate realistic-looking SR images as in [129], dilated convolution was used to double the receptive field, which resulted in better results.”
MethodRetractedGenerative Adversarial Networks and Perceptual Losses for Video Super-Resolution
Lucas, A., López-Tapia, S., Molina, R., & Katsaggelos, A. K. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2895768 · Cited by 203
“[21] have proposed to train a convolutional neural network to predict the perceptual similarity between a reference image and a distorted one [22], where the correct labels were obtained from large subjective studies given to humans.”
BackgroundA cross Transformer for image denoising
Tian, C., Zheng, M., Zuo, W., Zhang, Y., Zhang, Y., & Lin, C. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.102043 · Cited by 171
“, BM3D[11], WNNM [15], trainable nonlinear reaction diffusion (TNRD)[9], DnCNN[71], image restoration CNN (IRCNN) [72], FFDNet[73], enhanced convolutional neural denoising network (ECNDNet)[57], Dual denoising Network (DudeNet) [60], attention-guided denoising convolutional neural network (ADNet)[58], neural nearest n…”
BackgroundSelf-citationDeep Equilibrium Architectures for Inverse Problems in Imaging
Gilton, D., Ongie, G., & Willett, R. M. (2021) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2021.3118944 · Cited by 167
“Recent PnP and RED efforts focuses on using training data to learn denoisers [20, 21, 22, 23, 24].”
BackgroundUnpaired Learning of Deep Image Denoising
Wu, X., Liu, M., Cao, Y., Ren, D., & Zuo, W. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58548-8_21 · Cited by 185
“All these studies have consistently improved the denoising performance of deep networks [4,19,27,28,31,35,39,42].”
BackgroundSelf-citationUnsupervised Real-world Image Super Resolution via Domain-distance Aware Training
Wei, Y., Gu, S., Li, Y., Timofte, R., Jin, L., & Song, H. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.01318 · Cited by 168
“Benefiting from the rapid development of deep convolutional neural networks (CNNs), recent years have witnessed an explosive spread of training CNN models [27, 38, 48, 52, 60, 63, 57, 36] for SR.”
BackgroundSelf-citation
Metadata
- Authors
- Zhang, K., Zuo, W., Gu, S., & Zhang, L.
- Affiliations
- Hong Kong Polytechnic University (HK)
- Harbin Institute of Technology (CN)
- Venue
- 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2017-07
- Pages
- 2808-2817
- OpenAlex
- W2613155248
- Cited by
- 2,116
- References
- 81
- Citations by year
- 2026: 80 · 2025: 191 · 2024: 248 · 2023: 293 · 2022: 272 · 2021: 338 · 2020: 297 · 2019: 240 · 2018: 135 · 2017: 10
- FWCI
- 49.67
- Type
- conference paper
- Language
- en
- Open access
- green
- hdl.handle.net
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- PolyU Institutional Research Archive (Hong Kong Polytechnic University) (submittedVersion)
- TUScholarShare (Temple University) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Signal Denoising Methods
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image Processing Techniques
- Physical Sciences › Engineering › Media Technology › Advanced Image Fusion Techniques
- Keywords
- image restoration, model-based optimization, discriminative learning, variable splitting, inverse problems, low-level vision, Gaussian denoising, image deblurring
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-11, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-11 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
