Real Image Denoising With Feature Attention
Open accessAbstract
Deep convolutional neural networks perform better on images containing spatially invariant noise (synthetic noise); however, its performance is limited on real-noisy photographs and requires multiple stage network modeling. To advance the practicability of the denoising algorithms, this paper proposes a novel single-stage blind real image denoising network (RIDNet) by employing a modular architecture. We use residual on the residual structure to ease the flow of low-frequency information and apply feature attention to exploit the channel dependencies. Furthermore, the evaluation in terms of quantitative metrics and visual quality on three synthetic and four real noisy datasets against 19 state-of-the-art algorithms demonstrate the superiority of our RIDNet.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
RIDNet is more efficient and flexible and handles variant and invariant noises with better performance regardless of noise standard deviation compared to existing denoisers.
“Comparing to the existing denoisers (Guo et al. 2019; Zhang et al. 2017), the single-stage RIDNet (Anwar and Barnes 2019) is proven to be more efficient and flexible and can handle both variant and invariant noises with better performance regardless of the noise standard deviation.”
From Noise Based Deepfake Detection via Multi-Head Relative-Interaction (2023) · cites this paper as Anwar and Barnes 2019
The Noisy section describes RIDNet as an efficient model for synthetic and real noise, and the Conclusion identifies it as a single-stage blind denoiser. The grayscale comparisons report better results than the tested methods at noise standard deviations of 15, 25, and 50; the real-image experiments address spatially variant noise. The paper does not establish better performance regardless of standard deviation, or show that RIDNet is more efficient and flexible than all existing denoisers. (LLM, conf=0.86)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
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 · see citing works
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · see citing works
Image Super-Resolution Using Deep Convolutional Networks
Dong, C., Loy, C. C., He, K., & Tang, X. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2439281 · Cited by 10,105 · see citing works
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhutdinov, R., Zemel, R., & Bengio, Y. (2015) · arXiv · doi:10.48550/arxiv.1502.03044 · Cited by 8,248 · see citing works
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1512.03385 · Cited by 4,196 · see citing works
Weighted Nuclear Norm Minimization with Application to Image Denoising
Gu, S., Zhang, L., Zuo, W., & Feng, X. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.366 · Cited by 2,316 · see citing works
Learning Deep CNN Denoiser Prior for Image Restoration
Zhang, K., Zuo, W., Gu, S., & Zhang, L. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.300 · Cited by 2,116 · cited 10× · see citing works
“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.”
BackgroundMethodInfluentialShrinkage Fields for Effective Image Restoration
Schmidt, U., & Roth, S. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.349 · Cited by 543 · see citing works
Flagged first, then by citations
Research works printed but not linked: 36
- Abdelrahman Abdelhamed, Stephen Lin, and Michael S Brown. A high-quality denoising dataset for smartphone cameras. In CVPR, 2018. 5, 8
- Eirikur Agustsson and Radu Timofte. Ntire 2017 challenge on single image super-resolution: Dataset and study. In CVPR Workshops, 2017. 5
- Josue Anaya and Adrian Barbu. Renoir-a dataset for real low-light image noise reduction. Journal of Visual Commu- nication and Image Representation, 2018. 5
- Saeed Anwar, C Huynh, and Fatih Porikli. Combined in- ternal and external category-specific image denoising. In BMVC, 2017. 2
- Saeed Anwar, Cong Phouc Huynh, and Fatih Porikli. Chain- ing identity mapping modules for image denoising. arXiv preprint arXiv:1712.02933, 2017. 2, 3, 7 · arXiv
- Tim Brooks, Ben Mildenhall, Tianfan Xue, Jiawen Chen, Dillon Sharlet, and Jonathan T Barron. Unprocessing im- ages for learned raw denoising. In CVPR, 2019. 2
- Antoni Buades, Bartomeu Coll, and Jean-Michel Morel. A non-local algorithm for image denoising. In CVPR, 2005. 1, 2
- Harold Christopher Burger, Christian J Schuler, and Stefan Harmeling. Image denoising: Can plain neural networks compete with bm3d? In CVPR, 2012. 1, 2, 5, 6, 7
- Vladimir Bychkovsky, Sylvain Paris, Eric Chan, and Frédo Durand. Learning photographic global tonal adjustment with a database of input/output image pairs. In CVPR, 2011. 5
- Yunjin Chen and Thomas Pock. Trainable nonlinear reaction diffusion: A flexible framework for fast and effective image restoration. TPAMI, 2017. 1, 2, 5, 6, 7
- Weisheng Dong, Xin Li, D. Zhang, and Guangming Shi. Sparsity-based image denoising via dictionary learning and structural clustering. In CVPR, 2011. 2
- L. Zhang F. Chen and H. Yu. External Patch Prior Guided Internal Clustering for Image Denoising. In ICCV, 2015. 2
- Rafael C Gonzalez and Paul Wintz. Digital image process- ing (book). Reading, Mass., Addison-Wesley Publishing Co., Inc.(Applied Mathematics and Computation, 1977. 1
- Shi Guo, Zifei Yan, Kai Zhang, Wangmeng Zuo, and Lei Zhang. Toward convolutional blind denoising of real pho- tographs. arXiv preprint arXiv:1807.04686, 2018. 1, 2, 3, 5, 7, 8 · arXiv
- Jie Hu, Li Shen, and Gang Sun. Squeeze-and-excitation net- works. In CVPR, 2018. 4
- Jianbo Jiao, Wei-Chih Tu, Shengfeng He, and Rynson WH Lau. Formresnet: Formatted residual learning for image restoration. In CVPR Workshops, 2017. 2, 3
- M Lebrun, Antoni Buades, and Jean-Michel Morel. A non- local bayesian image denoising algorithm. SIAM Journal on Imaging Sciences, 2013. 2
- Stamatios Lefkimmiatis. Non-local color image denoising with convolutional neural networks. CVPR, 2016. 2, 5, 7
- A. Levin and B. Nadler. Natural image denoising: Optimal- ity and inherent bounds. In CVPR, 2011. 2
- Bee Lim, Sanghyun Son, Heewon Kim, Seungjun Nah, and Kyoung Mu Lee. Enhanced deep residual networks for single image super-resolution. In CVPR workshops, 2017. 1, 4
- Julien Mairal, Francis Bach, Jean Ponce, Guillermo Sapiro, and Andrew Zisserman. Non-local sparse models for image restoration. In ICCV, 2009. 2
- D. Martin, C. Fowlkes, D. Tal, and J. Malik. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecologi- cal statistics. In ICCV, 2001. 5, 6
- Seonghyeon Nam, Youngbae Hwang, Yasuyuki Matsushita, and Seon Joo Kim. A holistic approach to cross-channel im- age noise modeling and its application to image denoising. In CVPR, 2016. 5, 8
- Yigang Peng, Arvind Ganesh, John Wright, Wenli Xu, and Yi Ma. Rasl: Robust alignment by sparse and low-rank de- composition for linearly correlated images. TPAMI, 2012. 1
- Tobias Plötz and Stefan Roth. Benchmarking denois- ing algorithms with real photographs. arXiv preprint arXiv:1707.01313, 2017. 5, 7 · arXiv
- Tobias Plötz and Stefan Roth. Neural nearest neighbors net- works. In NIPS, 2018. 2
- Yaniv Romano, Michael Elad, and Peyman Milanfar. The little engine that could: Regularization by denoising (red). SIAM Journal on Imaging Sciences, 2017. 1
- Stefan Roth and Michael J Black. Fields of experts. IJCV, 2009. 1, 2, 5, 6, 7
- Yair Weiss and William T Freeman. What makes a good model of natural images? In CVPR, 2007. 1
- Jun Xu, Hui Li, Zhetong Liang, David Zhang, and Lei Zhang. Real-world noisy image denoising: A new bench- mark. arXiv preprint arXiv:1804.02603, 2018. 5 · arXiv
- Jun Xu, Lei Zhang, and David Zhang. A trilateral weighted sparse coding scheme for real-world image denoising. In ECCV, 2018. 7
- Jun Xu, Lei Zhang, David Zhang, and Xiangchu Feng. Multi-channel weighted nuclear norm minimization for real color image denoising. In ICCV, 2017. 7
- Jun Xu, Lei Zhang, Wangmeng Zuo, David Zhang, and Xi- angchu Feng. Patch Group Based Nonlocal Self-Similarity Prior Learning for Image Denoising. In ICCV, 2015. 2
- H. Yue, X. Sun, J. Yang, and F. Wu. Cid: Combined im- age denoising in spatial and frequency domains using web images. In CVPR, June 2014. 1
- Yulun Zhang, Kunpeng Li, Kai Li, Lichen Wang, Bineng Zhong, and Yun Fu. Image super-resolution using very deep residual channel attention networks. arXiv preprint arXiv:1807.02758, 2018. 4 · arXiv
- Daniel Zoran and Yair Weiss. From learning models of natu- ral image patches to whole image restoration. In ICCV, 2011. 1, 2, 5, 6, 7
Cited by
Sorted by citations
Noise Based Deepfake Detection via Multi-Head Relative-Interaction
Wang, T., & Chow, K. P. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i12.26701 · Cited by 93 · see citing works
“As a result, the proposed Deepfake detection model with RIDNet has shown dominant performance against that with CBDNet and DnCNN for both in-dataset and cross-dataset evaluations.”
MethodInfluentialYan, Y., Wang, D., Zhou, G., & Chen, Q. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3107586 · Cited by 60 · see citing works
ISP Meets Deep Learning: A Survey on Deep Learning Methods for Image Signal Processing
Santos, C. F. G. D., Arrais, R. R., Silva, J. V. S. D., Silva, M. H. M. D., Neto, W. B. G. D. A., Lopes, L. T., Bileki, G. A., Lima, I. O., Rondon, L. B., Souza, B. M. D., et al. (2025) · ACM Computing Surveys · doi:10.1145/3708516 · Cited by 9 · see citing works
“CycleISP achieved better results in both scenarios, with almost a 5 times smaller network parameters number than the previous best RAW denoising method [58] and performance gain against the previous best sRGB denoising algorithm [57].”
- Authors
- Anwar, S., & Barnes, N.
- Affiliations
- Australian National University (AU)
- Venue
- 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2019-10
- Pages
- 3155-3164
- OpenAlex
- W2940805846
- Cited by
- 784
- References
- 8
- Citations by year
- 2026: 75 · 2025: 127 · 2024: 140 · 2023: 159 · 2022: 126 · 2021: 87 · 2020: 67 · 2019: 3
- FWCI
- 23.07
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- ANU Open Research (Australian National University) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Signal Denoising Methods
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Enhancement Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image Processing Techniques
- Keywords
- blind image denoising, feature attention, channel dependencies, synthetic noise
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.
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
