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
25 Own interpretation · 16 Own result · 10 No basis given · 9 No full text of the sources · 3 Sources not found · 3 Own method · 2 Not checked yet · 1 Supported · 1 Not supported · 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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- 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
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- 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.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a 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
“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.
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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
“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
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a 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
“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.
plainconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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 the proposed denoiser is very competitive in both CPU and GPU implementation.”
§ Learning Deep CNN Denoiser Prior for Image Restoration > 4.1. Image Denoising
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a 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
“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.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says 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
“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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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 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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- 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)
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It 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
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It 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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It 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
plainn = 2- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It 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
plainSingle case- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It 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
plaindirectSingle case- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It 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
plaindirectSingle case- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It 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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It 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?
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It 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?
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably 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?
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably 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.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It 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.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably 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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably 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.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably 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
plaindirectn = 2- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably 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
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably 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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably 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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It 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.”
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
Items 2,001–2,094 of 2,094
SDE Diffusion Models for SAR Image Active Jamming Suppression With Pseudo-Paired SAR Images
Lin, X., Ren, D., Lang, P., et al. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3649264
“Nowadays, many state-of-the-art image restoration methods rely on neural networks [35], [36], using advanced architectures like convolutional neural networks (CNNs) [37], [38] and transformers [39], [40].”
Jung, D., Guezzi, N., Lee, S., Muhammad, N., Bae, S., & Yu, J. (2025) · Ultrasonic Imaging · doi:10.1177/01617346251398442
“However, FFDNet, IRCNN, and ECNDNet exhibit loss or distortion of fine vascular structures in the lower region (30– 50 mm).”
InfluentialAll-in-One Image Restoration via Frequency Domain Decomposition
Wang, W., Dong, R., & Wang, H. (2025) · 2022 IEEE 20th International Conference on Industrial Informatics (INDIN) · doi:10.1109/indin64977.2025.11279637
Liu, Y. (2026) · Journal on Advances in Signal Processing · doi:10.1186/s13634-025-01278-9
“• Plug-and-Play (PnP) Priors The PnP framework [41, 48] decouples the data fidelity and prior terms in an optimization algorithm.”
Self-Supervised Terahertz medical Image Denoising Based on Attention Mechanism and DnCNN
Tan, T., Tan, Y., Zhong, Y., et al. (2025) · doi:10.1145/3777577.3777668
“…image denoising methods, including one non-local similarity-based method (i.e., BM3D [22]), and three deep learning methods (i.e., DnCNN [6], IRCNN [23], and FFDNet [24]) The source codes or pre-trained models for each method were acquired from the official websites provided by the respective…”
Wang, H., Qu, H., Qi, L., et al. (2026) · Signal Processing Image Communication · doi:10.1016/j.image.2026.117484
Lohitha, N., Kirthi, P., Chary, P. A., et al. (2025) · doi:10.1109/resgenxai64788.2025.11344006
Exploring the transformer-based and diffusion-based models for single image deblurring
Park, S., Shin, C., Lew, J., & Yoon, S. (2026) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2026.104735
Wu, H., Huang, S., Guo, X., et al. (2026) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2025.104630
Li, Z., & Zhao, W. (2026) · npj Heritage Science · doi:10.1038/s40494-026-02361-6
“For comparative analysis, the IRCNN method 16 was employed as a baseline.”
A Model-Guided Neural Network Method for the Inverse Scattering ProblemPreprint
Tsang, O., Melia, O., Charisopoulos, V., Hoskins, J. G., Khoo, Y., & Willett, R. M. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6239014
ADF-SN: An Adaptive Dual-Domain Fusion and Self-Supervised Network for Wafer Image Denoising
Li, Z., Zhan, Q., He, Q., et al. (2026) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2026.3662874
“Later methods, such as FFDNet [21] and IRCNN, improved generalization and computational e ffi ciency [22].”
ATD: Improved Transformer With Adaptive Token Dictionary for Image Restoration
Zhang, L., Long, W., Li, Y., et al. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3669974 · Cited by 1
“Residual learning are adopted in [2], [9], while deeper architectures based on residual-in-residual and residual dense blocks are designed in [3], [66] to further stabilize the training process.”
Self-citationHybrid Reinforcement Learning to Optimize for Physics-Constrained Spectral Analysis
Chu, A., & Stork, W. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11401765
“For example, [27] utilized reinforcement learning to adapt step sizes in SGD while [28] embedded a CNN denoiser as a learned prior into classical optimization schemes for image restoration tasks, both yielding improved performance.”
Enhancing Image Denoising with Eight-Neighborhood Edge Feature Fusion and Gaussian Blur
Zhou, G., Du, Z., He, J., Li, Q., Xu, Y., & Deng, J. (2025) · International Conference on the Frontiers of Electronic, Electrical and Information Engineering (ICFEEIE) · doi:10.1109/icfeeie66944.2025.00024
“For instance, the Denoising Convolutional Neural Network (DnCNN) algorithm leverages the powerful feature extraction capabilities of deep convolutional neural networks, delivering exceptional performance in noise reduction[4, 16, 17].”
Gupta, R., & Sharma, S. J. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-33172-5.00009-1
An Inpainting Model of Fractal Group Sparse Representation Combined With Residual Denoising Network
Li, Z., & Zhao, W. (2026) · Journal of Engineering · doi:10.1155/je/7540384
Color image denoising by deep CNN prior and saturation-value total variation
Wang, W., Yang, C., & Yang, Y. (2026) · Inverse Problems and Imaging · doi:10.3934/ipi.2026026
Learning-based representations and methods for 3D shape analysis, manipulation and reconstruction
Rakotosaona, M. (2021) · theses.fr (ABES) · doi:10.70675/9f9943a6z9cc3z47afz802dzd6887d387ca3
Zhang, Y. (2022) · theses.fr (ABES) · doi:10.70675/ac894ad0z9abez4fd4z93aaza19f9f2c6f79
Single-pixel imaging : Compressed video acquisition and reconstruction using deep learning
Mur, A. L. (2021) · theses.fr (ABES) · doi:10.70675/db8ede94z2855z4bdbza5bdz1f163aa5acd1
Multimodal Document Understanding with Unified Vision and Language Cross-Modal Learning
Bakkali, S. (2022) · theses.fr (ABES) · doi:10.70675/aeb1fb70za11fz410fzaf33z6a28e0f0f154
Deep learning for embedded image compression in Earth Observation
de Oliveira, V. A. (2022) · theses.fr (ABES) · doi:10.70675/f9a47da0z6a4fz40eaz805ez33287fd80bc5
Novel Prospects of Image Restoration Inspired by Concepts of Quantum Mechanics
Dutta, S. (2023) · theses.fr (ABES) · doi:10.70675/8fe483d0z8da8z4b27z9b57z484d2a51ec01
Joint modeling and learning approaches for hyperspectral imaging and changepoint detection
Wang, X. (2024) · theses.fr (ABES) · doi:10.70675/ee98a9fez3898z4c13z9a8fzef7101876c8f
Maier, A., Christlein, V., Breininger, K., Würfl, T., Unberath, M., & Rieß, C. (2026) · doi:10.1515/9783111386690-021
MHAFNet: multi-stage hybrid attention and adaptive feature fusion network for image restoration
Huang, J., Shen, J., Wang, M., et al. (2026) · Scientific Reports · doi:10.1038/s41598-026-47500-y
Deep Learning Model for Predicting Foreign Language Enjoyment Using Eye-Tracking Data
Riadh, H., Bouzayenne, A., & Soui, M. (2025) · IEEE Afro-Mediterranean Conference on Artificial Intelligence (AMCAI) · doi:10.1109/amcai66110.2025.11474319
“Deep Neural Networks (DNNs) have previously been reported to perform better in emotion recognition tasks such as emotion classification from facial expressions, speech, and physiological signals [21,22].”
HSFM: Hybrid Spatial Frequency Mamba for Efficient Image Restoration
Yang, J., Liu, C., Liu, X., et al. (2026) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2026.3684375
“Baselines: For synthetic noise removal, we adopt four representative CNN-based methods (i.e., IRCNN [43], FFDNet [44], DnCNN [45] and DRUNet [46]), three transformer-based meth-ods (i.e., SwinIR [24], Restormer [7] and ART [47]) and two Mamba-based methods (i.e., MambaIR [10], MaIR [11]) as the…”
SRFormerV2: Taking a Closer Look at Permuted Self-Attention for Image Super-Resolution
Zhou, Y., Li, Z., Guo, C., Liu, L., Cheng, M., & Hou, Q. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3685679 · Cited by 16
Suzuki, Y., & Ono, S. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11465057
Dk-SSN: Data-Curvature Driven K-Stage Semi-Smooth Newton Unrolling for Image Denoising
Kumar, K. D., Phogat, S., & Sahoo, S. K. (2026) · National Conference on Communications · doi:10.1109/ncc68160.2026.11478992
“Early CNN-based approaches such as DnCNN [5], FFDNet [6], and IRCNN [7] showed that feed-forward architectures can provide strong restoration quality with fast inference.”
Shimizu, H., & Yukawa, M. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463357
Ultrasound Image Despeckling Using Deep Reinforcement Learning
Jarosik, P., Lewandowski, M., Klimonda, Z., et al. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461487
NUNSRN: Non-uniform and noise sensing restoration network for single-lens imaging
Li, Z., Tan, F., Zhang, R., et al. (2026) · Optics & Laser Technology · doi:10.1016/j.optlastec.2026.115340
Learning Latent Space for Multi-Order / Resolution Graph-Regularized Image Denoiser
Do, T. T., & Cheung, G. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461379
IR-SPC: Image Restoration With Starting Point Controlled Diffusion Model
Yang, C., Liang, L., Liu, S., Zhang, L., & Su, Z. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3686668
“Such as DnCNN [36], IRCNN [71], FFDNet [37], ADNet [72], SwinIR [49], Restormer [50] and PRTD [56].”
Self-citationDeep SNR-estimation for Wiener filter-based non-blind image deconvolution
Meyer, J., Dippon, L., Kludt, C., et al. (2026) · Signal Image and Video Processing · doi:10.1007/s11760-026-05360-z
“Zhang et al. [8] combine the strengths of model-based optimization with discriminatively trained deep learning denoisers.”
U-Shaped Transformer Image Denoising Network with Decoder-Side Pre-Fusion Calibration
Cui, P., Meng, Q., & Gao, C. (2026) · Applied Sciences · doi:10.3390/app16094523
Prompting Rain Off: Evolving Compact Dual Prompts for Continual De-Raining
Liu, M., Yang, W., & Liu, J. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3689428
“Based on the Maximum a Posteriori (MAP) principle [28], these methods optimize functions to get rain-free images [29].”
Zou, Z., Zhan, J., Zhou, Y., et al. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3692975
“Various architectures, including convolution-based networks [9], transformer-based models [10], and more recently, di ff usion-based frameworks [11], [12], have been proposed to reconstruct high-quality RS images from their corrupted counterparts.”
GD-NeRF: Grid-Based Deblurring for Neural Radiance Fields
Deng, T., Zhou, T., Yang, Z., et al. (2025) · Asian Conference on Artificial Intelligence Technology (ACAIT) · doi:10.1109/acait67930.2025.11522030
“Existing deblurring methods can be broadly categorized into two types: blind deblurring [11], [12] and non-blind deblurring [13]–[16].”
Introduction of a Learned Prior to Passive Cavitation Imaging
Lachambre, C., Gilles, B., Nicolas, B., et al. (2026) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi61048.2026.11515999
Fast Augmented Lagrangian Primal Dual Algorithm for Mean Curvature Regularization Model
Lu, T., Zhang, J., Duan, Y., et al. (2026) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-026-01304-x
“We benchmark our method against several representative deep learning approaches, including DnCNN [37], IRCNN [38], and CBDNet [14].”
Soft Routing Attention Network with Passive-Active Encoding for Image Denoising
Wang, Q., Quan, B., & Guo, S. (2026) · doi:10.1109/icnlp69856.2026.11527733
“Our method is compared against a comprehensive set of classical, CNN-based, and Transformer-based denoising approaches, including DnCNN [11], IRCNN [12], FFDNet [13], DSNet [14], BRD-Net [10], RNAN [15], RDN [16], IPT [17], DRUNet [18], and SwinIR [17].”
Chen, N., Zhang, Y., Chen, G., Zhao, J., Wang, C., Yazdani, A., & Wang, H. (2026) · IEEE Transactions on Emerging Topics in Computing · doi:10.1109/tetc.2026.3695050
“Restrictions apply. to clean images [38].”
Product-of-Gaussian-mixture diffusion models for joint nonlinear MRI reconstruction
Nagler, L., Zach, M., & Pock, T. (2026) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-026-01297-7
Enhancing lightweight image super-resolution through frequency-enhanced mamba networks
Wu, X., Yang, J., & Zhang, D. (2026) · The Visual Computer · doi:10.1007/s00371-026-04517-8
Learning Depth from Focus with Multi-Candidate Estimation and Proximal Refinement
Mahmood, M. T. (2026) · Electronics · doi:10.3390/electronics15122548
Multi-Scene Separation and Reconstruction From the Fused Random Compressed Measurements
Chen, C., Chen, Z., Hu, T., et al. (2026) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2026.3702099
“Restrictions apply. the prior term R ( x ) [25].”
Rasool, M. J. A., Ahmad, S., Ahamed, M. J. A., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-13654-1_13
RELD: Regularization by Latent Denoising
Cascarano, P., Stacchio, L., Sebastiani, A., et al. (2026) · IEEE Signal Processing Letters · doi:10.1109/lsp.2026.3705374
“For these two approaches we consider the set of CNN denoisers introduced in [36] as priors.”
Liangju, 许. X., & Shuhui, 高. G. (2026) · Laser & Optoelectronics Progress · doi:10.3788/lop252493
Li, Y., Wang, X., Geng, J., et al. (2026) · Electronics Letters · doi:10.1049/ell2.70657
YeTI: You Only Need Two Noisy Images for Real-World sRGB Noise Generation
Ko, J., Lim, B. W., Lee, S., Kim, D., & Kim, T. H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37350-2_28
Robust Plug-and-Play Framework for Adaptive Image Restoration
Zhou, Q., Sun, J. F., Ran, Y., Guo, Z., & Wu, B. H. (2026) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-026-01317-6
“By integrating it into the HQS iterative framework, methods such as IRCNN [12] and DPIR [13] demonstrate the effectiveness of Plug-and-Play priors for image restoration.”
CUST: Clustered Unit-Level Similarity Transformer for Lightweight Image Super-Resolution
Kim, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37624-4_26
DCTDBN: Explicit Frequency Decoupling and Adaptive Spatial–Frequency Fusion for Image DenoisingPreprint
Sheng, A., Wei, P., Li, X., yan, Z., & Xu, J. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7149775
Si, J., & Kim, S. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.115995
IRCDG: Adaptive all-in-one image restoration via component-divided guidance
Sun, W., Gao, X., Li, H., et al. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.114488
A Learned ADMM Framework with Fractional-Order Convolutional Regularization for Image Denoising
Laghrib, A. (2026) · The Visual Computer · doi:10.1007/s00371-026-04650-4
“Representative architectures include convolutional neural networks (CNNs) [9], residual networks [10], generative adversarial networks (GANs) [11], and, more recently, transformer-based models [12, 13], all of which have demonstrated remarkable empirical performance across a wide range of image…”
IDANet: Identity-Driven Attention Network for Unsupervised Synthetic Noise Removal
Akhilaraj, D., & Zacharias, J. (2025) · doi:10.1145/3774521.3774592
“IRCNN[62] follows a similar principle, using residual learning with hybrid dilated convolutions to enhance receptive field without increasing depth.”
A Plug-and-Play Method with Inpainting Network for Bayesian Uncertainty Quantification in Imaging
Wang, X., Tang, M., & Repetti, A. (2026) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-026-01330-9
“Following a Bayesian framework, the posterior distribution combines likelihood p ( y | x ) and prior p ( x ) distributions using the Bayes’ theorem, i.e.,”
Non-smooth image restoration via Nesterov-smoothed Bilevel Learnable Descent Algorithm
Khaider, B., Laghrib, A., Hadri, A., et al. (2026) · Mathematics and Computers in Simulation · doi:10.1016/j.matcom.2026.07.036
prNet: Data-Driven Phase Retrieval via Stochastic Refinement
Kaya, M. O., & Öktem, F. S. (2026) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2026.3719489
“Subsequently, combining the flipped outputs with the original outputs allows us to obtain a more refined estimate.”
Physics-Aware Deep Learning for SAR and InSAR Remote Sensing: Models, Methods, and Open Challenges
Taricco, G. (2026) · Remote Sensing · doi:10.3390/rs18152567
Scalable Image Restoration and Enhancement towards Diverse Downstream Applications
Wang, J., Zhang, K., Zhang, K., Zhang, C., Li, B., Hu, W., & Maybank, S. J. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02957-2
“…the type of the degradation is known, and often with a fixed distortion level, for example in image denoising (Zhang et al., 2022; Zamir et al., 2022; Zhang et al., 2017; Dong et al., 2019), image deraining (Han & Xiang, 2020; Chen et al., 2022; Fu et al., 2023; Xiao et al., 2023), image dehazing…”
Self-citationFuzzy-Clustering Attentive Network With Context-Aware Enhancement for Image Denoising
Han, Y., Jiang, B., Li, J., Zhang, B., & Lu, G. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3720520
Lightweight SNR-Adaptive Receiver-Side Enhancement for DeepJSCC-Based Wireless Image Transmission
Hou, S., Zhao, P., & Chen, N. (2026) · Sensors · doi:10.3390/s26165134
“Controlled comparison: DeepJSCC [7] and DnCNN [30], which use the same frozen DeepJSCC backbone as our method.”
Astronomical Image Denoising Using Physics-Guided Multi U-Net Models
Gadagkar, S., Inamdar, A., Ariga, P., & Hurakadli, S. (2026) · International Conference on Intelligent and Sustainable Electronics & Computing Technologies (INSECT) · doi:10.1109/insect68872.2026.11663578
“With the advent of deep learning, architectures like DnCNN [8], FFDNet [10], and IRCNN [11] have significantly improved the performance of image denoising systems by out-performing classical approaches due to much deeper feature representations combined with end-to-end learning strategies.”
Chen, K., Zhao, S., Wang, Y., et al. (2026) · International Journal of Remote Sensing · doi:10.1080/01431161.2026.2722344
Zhao, Z., Ren, H., Wu, Y., Zhu, Z., Chen, G., & Zhang, X. (2026) · Journal of Marine Science and Engineering · doi:10.3390/jmse14171614
Denoising Method for Low-Dose CT Image Using IRCNN Incorporated Edge Information
Sadamatsu, Y., Li, G., Murakami, S., et al. (2026) · International Workshop on Intelligent Systems (IWIS) · doi:10.1109/iwis70716.2026.11667757
“The backbone of the proposed network is IRCNN [4].”
A Data-Driven Loss Weighting Scheme Across Heterogeneous Tasks for Image Denoising
Rui, X., Cao, X., Zhao, X.-L., et al. (2026) · SIAM Journal on Imaging Sciences · doi:10.1137/25m178403x
SLER-IR: Spherical Layer-Wise Expert Routing for All-in-One Image Restoration
Peng, S., Lin, X., Luo, S., Ou, J., Zhang, D., Qi, L., Nguyen, T. Q., & Ren, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37627-5_26
Bayesian Self-Attention with Intra-Token Modeling for Lightweight Denoising Transformers
He, R., Shen, Z., & Ji, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37356-4_33
Wang, T., Xia, P., Tang, B., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37023-5_16
Self-citationMaximum a posteriori based unsupervised learning for images deblurring with cauchy noise
Zhang, M., Li, Y., Cui, Q., et al. (2026) · Applied Mathematics in Science and Engineering · doi:10.1080/27690911.2026.2730166
A hybrid Mamba–Transformer model for image restoration
Wen, J., Hou, W., Gool, L. V., et al. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.116091
Zhang, T., Fan, B., Su, Q., Chan, J., Jia, C., Zhao, X., Zhong, S., Zhang, A., Jiang, 边. B., & Liu, D. (2026) · Remote Sensing · doi:10.3390/rs18183171
Mengistu, S. T., & Flouris, K. (2026) · medRxiv · doi:10.64898/2026.09.14.26363026
Wang, Z., & Gao, X. (2026) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc70586.2026.11686502
“The proposed ADTNet is compared with the traditional model-based method BM3D [22], deep learning methods DnCNN [19], IRCNN [23], FFDNet [24], SwinIR [9], and deep unfolding methods DKSVD [10], CSCNet [25] and DCDicL [26].”
Enhanced Lightweight Image Super-Resolution via Residual Aggregation and Wavelet Loss
Nan, J.-H., Wang, W.-K., Zhang, F., et al. (2026) · Electronics · doi:10.3390/electronics15184271
Hu, Z., & Chai, L. (2026) · Sensors · doi:10.3390/s26196028
Trust Region Plug-and-Play With Provable Convergence for Image Restoration
Sabdana, C. B., Sunaryono, D., Amaliah, B., Sabilla, S. I., & Suciningtyas, L. (2026) · IEEE Access · doi:10.1109/access.2026.3737001
Dual-Domain-Based Plug-and-Play Image Restoration
Du, W., & Li, J. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3737047
“However, their performance is highly sensitive to mismatches between the training and test degradation distributions, and their generalizability across di ff erent operators A is limited [29], [30].”
InfluentialQiang, 冯. F., Guojia, 侯. H., Honghong, 孙. S., et al. (2026) · Laser & Optoelectronics Progress · doi:10.3788/lop260836
Progressive Focused Transformer for Image Restoration
Long, W., Zhang, J., Zhou, X., Zhang, L., & Gu, S. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-03053-1
Self-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
