Image denoising: Can plain neural networks compete with BM3D?
Abstract
Image denoising can be described as the problem of mapping from a noisy image to a noise-free image. The best currently available denoising methods approximate this mapping with cleverly engineered algorithms. In this work we attempt to learn this mapping directly with a plain multi layer perceptron (MLP) applied to image patches. While this has been done before, we will show that by training on large image databases we are able to compete with the current state-of-the-art image denoising methods. Furthermore, our approach is easily adapted to less extensively studied types of noise (by merely exchanging the training data), for which we achieve excellent results as well.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
Real-life dirt results showed that the proposed system removed most dirt noise while the MLP left many more unremoved.
“Real-life dirt results showed that the proposed system removed most dirt noise in the images, while the MLP left many more unremoved.”
From A Review of Detection and Removal of Raindrops in Automotive Vision Systems (2021) · cites this paper as [44]
Synthesized rain results showed that the proposed system outperformed the MLP system in removing more rain droplets and maintaining non-rain areas intact.
“Synthesized rain that the proposed system outperformed the MLP system, in terms of removing more rain droplets and maintain non-rain areas of the image intact.”
From A Review of Detection and Removal of Raindrops in Automotive Vision Systems (2021) · cites this paper as [44]
Synthetic dirt results showed that the proposed system and the MLP system outperformed the other three baseline methods.
“Synthetic dirt results showed that the proposed system and the MLP system outperformed the other three baseline methods.”
From A Review of Detection and Removal of Raindrops in Automotive Vision Systems (2021) · cites this paper as [44]
Cites
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · see citing works
Learning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892 · see citing works
Multilayer feedforward networks are universal approximators
Hornik, K., Stinchcombe, M., & White, H. (1989) · Neural Networks · doi:10.1016/0893-6080(89)90020-8 · Cited by 21,728 · see citing works
A fast learning algorithm for deep belief nets
Hinton, G. E., Osindero, S., & Teh, Y.-W. (2006) · Neural Computation · doi:10.1162/neco.2006.18.7.1527 · Cited by 16,336 · see citing works
$rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation
Aharon, M., Elad, M., & Bruckstein, A. M. (2006) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2006.881199 · Cited by 9,464 · see citing works
Image denoising by sparse 3-D transform-domain collaborative filtering
Dabov, K., Foi, A., Katkovnik, V., & Egiazarian, K. (2007) · IEEE Transactions on Image Processing · doi:10.1109/tip.2007.901238 · Cited by 9,283 · see citing works
Multilayer feedforward networks are universal approximators
HornikK., StinchcombeM., & WhiteH. (1989) · Neural Networks · doi:10.5555/70405.70408 · Cited by 9,266 · see citing works
Martin, D., Fowlkes, C., Tal, D., & Malik, J. (2002) · Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001 · doi:10.1109/iccv.2001.937655 · Cited by 8,216 · see citing works
Bilateral Filtering for Gray and Color Images
Tomasi, C., & Manduchi, R. (2002) · Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271) · doi:10.1109/iccv.1998.710815 · Cited by 8,177 · cited 1× · see citing works
“Numerous and diverse approaches exists: Some selectively smooth parts of a noisy image [25, 26].”
BackgroundImage Denoising Via Sparse and Redundant Representations Over Learned Dictionaries
Elad, M., & Aharon, M. (2006) · IEEE Transactions on Image Processing · doi:10.1109/tip.2006.881969 · Cited by 5,321 · see citing works
LabelMe: A Database and Web-Based Tool for Image Annotation
Russell, B. C., Torralba, A., Murphy, K. P., & Freeman, W. T. (2008) · International Journal of Computer Vision · doi:10.1007/s11263-007-0090-8 · Cited by 4,210 · see citing works
A Review of Image Denoising Algorithms, with a New One
Buades, A., Coll, B., & Morel, J. (2005) · Multiscale Modeling and Simulation · doi:10.1137/040616024 · Cited by 4,120 · see citing works
Image denoising using scale mixtures of gaussians in the wavelet domain
Portilla, J., Strela, V., Wainwright, M. J., & Simoncelli, E. P. (2003) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.818640 · Cited by 2,256 · see citing works
Anisotropic diffusion in image processing
Weickert, J. (1998) · Cited by 2,230 · see citing works
The PASCAL visual object classes challenge 2006 (VOC2006) results
Everingham, M., Zisserman, A., Williams, C. K. I., & Gool, L. V. (2006) · Cited by 2,079 · see citing works
Non-local sparse models for image restoration
Mairal, J., Bach, F., Ponce, J., Sapiro, G., & Zisserman, A. (2009) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2009.5459452 · Cited by 1,724 · see citing works
LeCun, Y., Bottou, L., Orr, G., & Müller, K. (1998) · neural information processing systems · Cited by 1,333 · see citing works
Roth, S., & Black, M. J. (2009) · International Journal of Computer Vision · doi:10.1007/s11263-008-0197-6 · Cited by 847 · see citing works
(2008) · Cited by 838 · see citing works
Traffic sign recognition with multi-scale Convolutional Networks
Sermanet, P., & LeCun, Y. (2011) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2011.6033589 · Cited by 771 · see citing works
Noise removal via Bayesian wavelet coring
Simoncelli, E. P., & Adelson, E. H. (2002) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.1996.559512 · Cited by 617 · see citing works
Optimal Inversion of the Anscombe Transformation in Low-Count Poisson Image Denoising
Makitalo, M. J., & Foi, A. (2010) · IEEE Transactions on Image Processing · doi:10.1109/tip.2010.2056693 · Cited by 353 · see citing works
A Biologically Inspired Algorithm for the Recovery of Shading and Reflectance Images
Olmos, A., & Kingdom, F. A. A. (2004) · Perception · doi:10.1068/p5321 · Cited by 342 · see citing works
What makes a good model of natural images?
Weiss, Y., & Freeman, W. T. (2007) · 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.2007.383092 · Cited by 308 · see citing works
Natural image denoising: Optimality and inherent bounds
Levin, A., & Nadler, B. (2011) · doi:10.1109/cvpr.2011.5995309 · Cited by 242 · see citing works
Noise estimation and removal in MR imaging: The variance-stabilization approach
Foi, A. (2011) · IEEE International Symposium on Biomedical Imaging: From Nano to Macro (ISBI) · doi:10.1109/isbi.2011.5872758 · Cited by 159 · see citing works
A Unified Energy-Based Framework for Unsupervised Learning
Ranzato, M., Boureau, Y.-L., Chopra, S., et al. (2007) · International Conference on Artificial Intelligence and Statistics · Cited by 105 · see citing works
Enhancement of JPEG-Compressed Images by Re-application of JPEG
Nosratinia, A. (2001) · The Journal of VLSI Signal Processing Systems for Signal Image and Video Technology · doi:10.1023/a:1008167430544 · Cited by 76 · see citing works
Image Denoising using a Neural Network Based Non-Linear Filter in Wavelet Domain
Zhang, S., & Salari, E. (2006) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2005.1415573 · Cited by 36 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Wang, X., Girshick, R., Gupta, A., & He, K. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00813 · Cited by 11,596 · see citing works
“BM3D is a solid image denoising baseline even compared with deep neural networks [5].”
BackgroundImage 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
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
Zhang, K., Zuo, W., Chen, Y., Meng, D., & Zhang, L. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2662206 · Cited by 8,983 · see citing works
LIME: Low-Light Image Enhancement via Illumination Map Estimation
Guo, X., Li, Y., & Ling, H. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2639450 · Cited by 2,998 · see citing works
Deep Convolutional Neural Network for Inverse Problems in Imaging
Jin, K. H., McCann, M. T., Froustey, E., & Unser, M. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2713099 · Cited by 2,529 · 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 · see citing works
Medical Image Denoising Using Convolutional Denoising Autoencoders
Gondara, L. (2016) · 2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW) · doi:10.1109/icdmw.2016.0041 · Cited by 737 · see citing works
Attention-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 · see citing works
Araya-Polo, M., Jennings, J., Adler, A., & Dahlke, T. (2018) · The Leading Edge · doi:10.1190/tle37010058.1 · Cited by 558 · see citing works
PANDA: Pose Aligned Networks for Deep Attribute Modeling
Zhang, N., Paluri, M., Ranzato, M., Darrell, T., & Bourdev, L. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.212 · Cited by 495 · see citing works
Restoring an Image Taken through a Window Covered with Dirt or Rain
Eigen, D., Krishnan, D., & Fergus, R. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.84 · Cited by 454 · see citing works
A Machine Learning Approach for Non-blind Image Deconvolution
Schuler, C. J., Burger, H. C., Harmeling, S., & Scholkopf, B. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.142 · Cited by 319 · see citing works
Self-citationStudying Very Low Resolution Recognition Using Deep Networks
Wang, Z., Chang, S., Yang, Y., Liu, D., & Huang, T. S. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.518 · Cited by 235 · see citing works
Wang, X., Girshick, R., Gupta, A., & He, K. (2017) · arXiv · Cited by 11,689 · see citing works
Convolutional auto-encoder for image denoising of ultra-low-dose CT
Nishio, M., Nagashima, C., Hirabayashi, S., Ohnishi, A., Sasaki, K., Sagawa, T., Hamada, M., & Yamashita, T. (2017) · Heliyon · doi:10.1016/j.heliyon.2017.e00393 · Cited by 106 · see citing works
Enhanced bi-prediction with convolutional neural network for high-efficiency video coding
Zhao, Z., Wang, S., Wang, S., Zhang, X., Ma, S., & Yang, J. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2018.2876399 · Cited by 75 · see citing works
Zhang, J., Cao, Y., Wang, Y., Wen, C., & Chen, C. W. (2018) · Proceedings of the 26th ACM international conference on Multimedia · doi:10.1145/3240508.3240653 · Cited by 40 · see citing works
A Review of Detection and Removal of Raindrops in Automotive Vision Systems
Hamzeh, Y., & Rawashdeh, S. A. (2021) · Journal of Imaging · doi:10.3390/jimaging7030052 · Cited by 21 · see citing works
“Systems based on conventional neural networks (NN) were also proposed for image denoising, such as the Multi-layer perceptron (MLP) [44] and Block-matching and 3D filtering (BM3D) [45].”
BackgroundMethodInfluentialStd-net: spatio-temporal decomposition network for video demoiréing with sparse transformers
Niu, Y., Xu, R., Lin, Z., & Liu, W. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3386604 · Cited by 12 · see citing works
- Authors
- Burger, H. C., Schuler, C. J., & Harmeling, S.
- Affiliations
- Max Planck Institute for Intelligent Systems (DE)
- Venue
- 2012 IEEE Conference on Computer Vision and Pattern Recognition
- Publisher
- IEEE
- Published
- 2012-06
- Pages
- 2392-2399
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2037642501
- Semantic Scholar
- 1d70937202d843664c5591fde4fb0d48627d1cf6
- Cited by
- 1,325
- References
- 29
- Citations by year
- 2026: 27 · 2025: 70 · 2024: 68 · 2023: 94 · 2022: 125 · 2021: 147 · 2020: 184 · 2019: 196 · 2018: 161 · 2017: 105 · 2016: 79 · 2015: 36 · 2014: 20 · 2013: 12 · 2012: 1
- FWCI
- 15.61
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- MPG.PuRe (Max Planck Society) (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 › Image Enhancement Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image Processing Techniques
- Keywords
- image denoising, BM3D, multilayer perceptron, image patches, noise modeling, deep learning denoising
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
