# Learning Degradation-Independent Representations for Camera ISP Pipelines

arXiv: https://arxiv.org/abs/2307.00761 · HTML: https://mlsanity.com/paper/2307.00761/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 57 references that are in the map.
- First posted on arXiv 3 Jul 2023.

## Builds on (most cited first, 30 of 33)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [Uformer: A General U-Shaped Transformer for Image Restoration](https://mlsanity.com/paper/2106.03106/) (2021)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [Designing a Practical Degradation Model for Deep Blind Image Super-Resolution](https://mlsanity.com/paper/2103.14006/) (2021)
- [f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization](https://mlsanity.com/paper/1606.00709/) (2016)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [Toward Convolutional Blind Denoising of Real Photographs](https://mlsanity.com/paper/1807.04686/) (2018)
- [Benchmarking Denoising Algorithms with Real Photographs](https://mlsanity.com/paper/1707.01313/) (2017)
- [Learning Robust Representations via Multi-View Information Bottleneck](https://mlsanity.com/paper/2002.07017/) (2020)
- [Learning a No-Reference Quality Metric for Single-Image Super-Resolution](https://mlsanity.com/paper/1612.05890/) (2016)
- [InfoVAE: Information Maximizing Variational Autoencoders](https://mlsanity.com/paper/1706.02262/) (2017)
- [Replacing Mobile Camera ISP with a Single Deep Learning Model](https://mlsanity.com/paper/2002.05509/) (2020)
- [DeepISP: Towards Learning an End-to-End Image Processing Pipeline](https://mlsanity.com/paper/1801.06724/) (2018)
- [Real-world Noisy Image Denoising: A New Benchmark](https://mlsanity.com/paper/1804.02603/) (2018)
- [Multitask AET with Orthogonal Tangent Regularity for Dark Object Detection](https://mlsanity.com/paper/2205.03346/) (2022)
- [ReconfigISP: Reconfigurable Camera Image Processing Pipeline](https://mlsanity.com/paper/2109.04760/) (2021)
- [Learning Invariant Representation for Unsupervised Image Restoration](https://mlsanity.com/paper/2003.12769/) (2020)
- [Variational Interaction Information Maximization for Cross-domain Disentanglement](https://mlsanity.com/paper/2012.04251/) (2020)
- [Automatic ISP image quality tuning using non-linear optimization](https://mlsanity.com/paper/1902.09023/) (2019)
- [Rawgment: Noise-Accounted RAW Augmentation Enables Recognition in a Wide Variety of Environments](https://mlsanity.com/paper/2210.16046/) (2022)
- [Learning Distortion Invariant Representation for Image Restoration from A Causality Perspective](https://mlsanity.com/paper/2303.06859/) (2023)
- [Measuring multivariate redundant information with pointwise common change in surprisal](https://mlsanity.com/paper/1602.05063/) (2016)
- [Deep Multi-modality Soft-decoding of Very Low Bit-rate Face Videos](https://mlsanity.com/paper/2008.01652/) (2020)

## Built on by (most cited first, 11 of 11)

- [RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images](https://mlsanity.com/paper/2408.14802/) (2024)
- [Towards RAW Object Detection in Diverse Conditions](https://mlsanity.com/paper/2411.15678/) (2024)
- [Dark-ISP: Enhancing RAW Image Processing for Low-Light Object Detection](https://mlsanity.com/paper/2509.09183/) (2025)
- [Disentangled Noisy Correspondence Learning](https://mlsanity.com/paper/2408.05503/) (2024)
- [RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images and A Benchmark](https://mlsanity.com/paper/2503.17027/) (2025)
- [Task-Aware Image Signal Processor for Advanced Visual Perception](https://mlsanity.com/paper/2509.13762/) (2025)
- [UniISP: A Unified ISP Framework for Both Human and Machine Vision](https://mlsanity.com/paper/2605.07359/) (2026)
- [Revealing Microscopic Objects in Fluorescence Live Imaging by Video-to-video Translation Based on A Spatial-temporal Generative Adversarial Network](https://mlsanity.com/paper/2502.16342/) (2025)
- [SemiISP/SemiIE: Semi-Supervised Image Signal Processor and Image Enhancement Leveraging One-to-Many Mapping sRGB-to-RAW](https://mlsanity.com/paper/2504.02345/) (2025)
- [Beyond Illumination: A Conditional Mutual Information-Guided Network for Low-Light Image Enhancement](https://mlsanity.com/paper/2608.01886/) (2026)
- [FreqAdapt: Frequency-Adaptive Processing for RAW Object Detection](https://mlsanity.com/paper/2608.03385/) (2026)

## Abstract (arXiv)

Image signal processing (ISP) pipeline plays a fundamental role in digital cameras, which converts raw Bayer sensor data to RGB images. However, ISP-generated images usually suffer from imperfections due to the compounded degradations that stem from sensor noises, demosaicing noises, compression artifacts, and possibly adverse effects of erroneous ISP hyperparameter settings such as ISO and gamma values. In a general sense, these ISP imperfections can be considered as degradations. The highly complex mechanisms of ISP degradations, some of which are even unknown, pose great challenges to the generalization capability of deep neural networks (DNN) for image restoration and to their adaptability to downstream tasks. To tackle the issues, we propose a novel DNN approach to learn degradation-independent representations (DiR) through the refinement of a self-supervised learned baseline representation. The proposed DiR learning technique has remarkable domain generalization capability and consequently, it outperforms state-of-the-art methods across various downstream tasks, including blind image restoration, object detection, and instance segmentation, as verified in our experiments.