The DOI matches its Crossref record; 42 of the 42 references it cites were found in a registry or an index.
Unprocessing Images for Learned Raw Denoising
Open accessAbstract
Machine learning techniques work best when the data used for training resembles the data used for evaluation. This holds true for learned single-image denoising algorithms, which are applied to real raw camera sensor readings but, due to practical constraints, are often trained on synthetic image data. Though it is understood that generalizing from synthetic to real images requires careful consideration of the noise properties of camera sensors, the other aspects of an image processing pipeline (such as gain, color correction, and tone mapping) are often overlooked, despite their significant effect on how raw measurements are transformed into finished images. To address this, we present a technique to “unprocess” images by inverting each step of an image processing pipeline, thereby allowing us to synthesize realistic raw sensor measurements from commonly available Internet photos. We additionally model the relevant components of an image processing pipeline when evaluating our loss function, which allows training to be aware of all relevant photometric processing that will occur after denoising. By unprocessing and processing training data and model outputs in this way, we are able to train a simple convolutional neural network that has 14%-38% lower error rates and is 9×-18× faster than the previous state of the art on the Darmstadt Noise Dataset, and generalizes to sensors outside of that dataset as well.
Overview
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
Verification
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.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741
The pascal visual object classes (VOC) challenge
Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2010) · International Journal of Computer Vision · doi:10.1007/s11263-009-0275-4 · Cited by 19,599
Nonlinear total variation based noise removal algorithms
Rudin, L. I., Osher, S., & Fatemi, E. (1992) · Physica D: Nonlinear Phenomena · doi:10.1016/0167-2789(92)90242-f · Cited by 15,704
Scale-space and edge detection using anisotropic diffusion
Perona, P., & Malik, J. (1990) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.56205 · Cited by 12,119
$rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation
Aharon, M., Elad, M., & Bruckstein, A. (2006) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2006.881199 · Cited by 9,451
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
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
A Non-Local Algorithm for Image Denoising
Buades, A., Coll, B., & Morel, J.-M. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.38 · Cited by 7,616
Cited by
Multi-Stage Progressive Image Restoration
Zamir, S. W., Arora, A., Khan, S., Hayat, M., Khan, F. S., Yang, M.-H., & Shao, L. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01458 · Cited by 2,095
NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections
Martin-Brualla, R., Radwan, N., Sajjadi, M. S. M., Barron, J. T., Dosovitskiy, A., & Duckworth, D. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00713 · Cited by 1,374
Self-citationPlug-and-Play Image Restoration With Deep Denoiser Prior
Zhang, K., Li, Y., Zuo, W., Zhang, L., Van Gool, L., & Timofte, R. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3088914 · Cited by 1,113
Deep Learning on Image Denoising: An overview
Tian, C., Fei, L., Zheng, W., Xu, Y., Zuo, W., & Lin, C.-W. (2020) · Neural Networks · doi:10.1016/j.neunet.2020.07.025 · Cited by 1,091
Learning Enriched Features for Real Image Restoration and Enhancement
Zamir, S. W., Arora, A., Khan, S., Hayat, M., Khan, F. S., Yang, M.-H., & Shao, L. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58595-2_30 · Cited by 946
Designing a Practical Degradation Model for Deep Blind Image Super-Resolution
Zhang, K., Liang, J., Van Gool, L., & Timofte, R. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00475 · Cited by 760
Artificial intelligence in the creative industries: a review
Anantrasirichai, N., & Bull, D. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-021-10039-7 · Cited by 793
Learning Enriched Features for Fast Image Restoration and Enhancement
Zamir, S. W., Arora, A., Khan, S., Hayat, M., Khan, F. S., Yang, M.-H., & Shao, L. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3167175 · Cited by 531
Learning to Restore Low-Light Images via Decomposition-and-Enhancement
Xu, K., Yang, X., Yin, B., & Lau, R. W. H. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00235 · Cited by 449
CycleISP: Real Image Restoration via Improved Data Synthesis
Zamir, S. W., Arora, A., Khan, S., Hayat, M., Khan, F. S., Yang, M.-H., & Shao, L. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00277 · Cited by 393
Benchmarking Low-Light Image Enhancement and Beyond
Liu, J., Xu, D., Yang, W., Fan, M., & Huang, H. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-020-01418-8 · Cited by 349
NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Images
Mildenhall, B., Hedman, P., Martin-Brualla, R., Srinivasan, P. P., & Barron, J. T. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01571 · Cited by 349
Self-citationDeep Generalized Unfolding Networks for Image Restoration
Mou, C., Wang, Q., & Zhang, J. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01688 · Cited by 290
Chen, C., Chen, Q., Do, M., & Koltun, V. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00328 · Cited by 282
FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation
Tassano, M., Delon, J., & Veit, T. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00143 · Cited by 276
Ji, K., Lin, W., Sun, Y., Cui, L.-S., Shamsi, J., Chiang, Y.-H., Chen, J., Tennyson, E. M., Dai, L., Li, Q., et al. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00736-z · Cited by 36
“While previous works that utilize noise parameter 23–26 or distortion kernels 27,28 for noise modelling are difficult to implement in real-world scenarios due to challenges in obtaining this information (Extended Data Table 1), our noise-level detector provides an automatic estimation of the noise…”
BackgroundSelf-citationRecaptured screen image demoiréing in raw domain
Yue, H., Cheng, Y., Mao, Y., Cao, C., & Yang, J. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3198333 · Cited by 26
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 15
“Besides, from these high-resolution RAW images was created the low-resolution RAW images through the bicubic downsampling kernel [94], mosaic kernel [58], and addition of the Gaussian-Poisson noise model [111].”
Influential
Metadata
- Authors
- Brooks, T., Mildenhall, B., Xue, T., Chen, J., Sharlet, D., & Barron, J. T.
- Venue
- 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2019-06
- Pages
- 11028-11037
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2901996700
- Cited by
- 473
- References
- 42
- FWCI
- 17.71
- Type
- conference paper
- Language
- en
- Open access
- green
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.