mlsanityData to 7 Oct 2026

Deep Contrastive Patch-Based Subspace Learning for Camera Image Signal Processing

arXiv 2104.00253 ↗First posted 1 Apr 2021eess.IV cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Camera Image Signal Processing (ISP) pipelines can get appealing results in different image signal processing tasks. Nonetheless, the majority of these methods, including those employing an encoder-decoder deep architecture for the task, typically utilize a uniform filter applied consistently across the entire image. However, it is natural to view a camera image as heterogeneous, as the color intensity and the artificial noise are distributed vastly differently, even across the two-dimensional domain of a single image. Varied Moire ringing, motion blur, color-bleaching, or lens-based projection distortions can all potentially lead to a heterogeneous image artifact filtering problem. In this paper, we present a specific patch-based, local subspace deep neural network that improves Camera ISP to be robust to heterogeneous artifacts (especially image denoising). We call our three-fold deep-trained model the Patch Subspace Learning Autoencoder (PSL-AE). The PSL-AE model does not make assumptions regarding uniform levels of image distortion. Instead, it first encodes patches extracted from noisy a nd clean image pairs, with different artifact types or distortion levels, by contrastive learning. Then, the patches of each image are encoded into corresponding soft clusters within their suitable latent sub-space, utilizing a prior mixture model. Furthermore, the decoders undergo training in an unsupervised manner, specifically trained for the image patches present in each cluster. The experiments highlight the adaptability and efficacy through enhanced heterogeneous filtering, both from synthesized artifacts but also realistic SIDD image pairs.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 34 of its 59 references that are in the map. First posted on arXiv 1 Apr 2021.

Builds on

34 of 59 references.

References · 34

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  4. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  5. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  6. 2019DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Bettercited by 361
  7. 2018Noise2Void - Learning Denoising from Single Noisy Imagescited by 359
  8. 2018Toward Convolutional Blind Denoising of Real Photographscited by 274
  9. 2019Noise2Self: Blind Denoising by Self-Supervisioncited by 274
  10. 2016Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clusteringcited by 237
  11. 2016Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoderscited by 219
  12. 2020CycleISP: Real Image Restoration via Improved Data Synthesiscited by 212
22 more
  1. 2017Benchmarking Denoising Algorithms with Real Photographscited by 209
  2. 2019Deep Learning on Image Denoising: An overviewcited by 128
  3. 2019Noisier2Noise: Learning to Denoise from Unpaired Noisy Datacited by 125
  4. 2020Spatially-Attentive Patch-Hierarchical Network for Adaptive Motion Deblurringcited by 119
  5. 2020Replacing Mobile Camera ISP with a Single Deep Learning Modelcited by 108
  6. 2017Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observationscited by 100
  7. 2018DeepISP: Towards Learning an End-to-End Image Processing Pipelinecited by 88
  8. 2020NBNet: Noise Basis Learning for Image Denoising with Subspace Projectioncited by 77
  9. 2020Noise2Same: Optimizing A Self-Supervised Bound for Image Denoisingcited by 56
  10. 2020Deep White-Balance Editingcited by 54
  11. 2018Learning Latent Subspaces in Variational Autoencoderscited by 51
  12. 2015Denoising Criterion for Variational Auto-Encoding Frameworkcited by 43
  13. 2017Deep Generative Adversarial Compression Artifact Removalcited by 37
  14. 2018Deep clustering: On the link between discriminative models and K-meanscited by 37
  15. 2019Deep Graph-Convolutional Image Denoisingcited by 32
  16. 2017Nonparametric Variational Auto-encoders for Hierarchical Representation Learningcited by 22
  17. 2019Learning Deformable Kernels for Image and Video Denoisingcited by 18
  18. 2019NLH: A Blind Pixel-level Non-local Method for Real-world Image Denoisingcited by 15
  19. 2020Relighting Images in the Wild with a Self-Supervised Siamese Auto-Encodercited by 13
  20. 2020PatchVAE: Learning Local Latent Codes for Recognitioncited by 10
  21. 2020Self-Supervised Poisson-Gaussian Denoisingcited by 9
  22. 2019Double cycle-consistent generative adversarial network for unsupervised conditional generationcited by 4

Built on by

Not cited yet.