# Self-Supervised Reversed Image Signal Processing via Reference-Guided Dynamic Parameter Selection

arXiv: https://arxiv.org/abs/2303.13916 · HTML: https://mlsanity.com/paper/2303.13916/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 56 references that are in the map.
- First posted on arXiv 24 Mar 2023.

## Builds on (most cited first, 30 of 37)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [Deep Layer Aggregation](https://mlsanity.com/paper/1707.06484/) (2017)
- [Dynamic Convolution: Attention over Convolution Kernels](https://mlsanity.com/paper/1912.03458/) (2019)
- [Unbiased Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2102.09480/) (2021)
- [CondConv: Conditionally Parameterized Convolutions for Efficient Inference](https://mlsanity.com/paper/1904.04971/) (2019)
- [Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design](https://mlsanity.com/paper/1902.00275/) (2019)
- [Unprocessing Images for Learned Raw Denoising](https://mlsanity.com/paper/1811.11127/) (2018)
- [CycleISP: Real Image Restoration via Improved Data Synthesis](https://mlsanity.com/paper/2003.07761/) (2020)
- [Benchmarking Denoising Algorithms with Real Photographs](https://mlsanity.com/paper/1707.01313/) (2017)
- [Cross-Domain Adaptive Teacher for Object Detection](https://mlsanity.com/paper/2111.13216/) (2021)
- [Zoom To Learn, Learn To Zoom](https://mlsanity.com/paper/1905.05169/) (2019)
- [Replacing Mobile Camera ISP with a Single Deep Learning Model](https://mlsanity.com/paper/2002.05509/) (2020)
- [Invertible Image Signal Processing](https://mlsanity.com/paper/2103.15061/) (2021)
- [DeepISP: Towards Learning an End-to-End Image Processing Pipeline](https://mlsanity.com/paper/1801.06724/) (2018)
- [You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction](https://mlsanity.com/paper/2205.14871/) (2022)
- [Unbiased Teacher v2: Semi-supervised Object Detection for Anchor-free and Anchor-based Detectors](https://mlsanity.com/paper/2206.09500/) (2022)
- [From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose Estimation](https://mlsanity.com/paper/2103.14843/) (2021)
- [Model-Based Image Signal Processors via Learnable Dictionaries](https://mlsanity.com/paper/2201.03210/) (2022)
- [Reconfiguring the Imaging Pipeline for Computer Vision](https://mlsanity.com/paper/1705.04352/) (2017)
- [ReconfigISP: Reconfigurable Camera Image Processing Pipeline](https://mlsanity.com/paper/2109.04760/) (2021)
- [CIE XYZ Net: Unprocessing Images for Low-Level Computer Vision Tasks](https://mlsanity.com/paper/2006.12709/) (2020)
- [DynamicISP: Dynamically Controlled Image Signal Processor for Image Recognition](https://mlsanity.com/paper/2211.01146/) (2022)

## Built on by (most cited first, 5 of 5)

- [RAW-Diffusion: RGB-Guided Diffusion Models for High-Fidelity RAW Image Generation](https://mlsanity.com/paper/2411.13150/) (2024)
- [A Learnable Color Correction Matrix for RAW Reconstruction](https://mlsanity.com/paper/2409.02497/) (2024)
- [PQDynamicISP: Dynamically Controlled Image Signal Processor for Any Image Sensors Pursuing Perceptual Quality](https://mlsanity.com/paper/2403.10091/) (2024)
- [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)
- [Linear Image Generation by Synthesizing Exposure Brackets](https://mlsanity.com/paper/2604.21008/) (2026)

## Abstract (arXiv)

Unprocessed sensor outputs (RAW images) potentially improve both low-level and high-level computer vision algorithms, but the lack of large-scale RAW image datasets is a barrier to research. Thus, reversed Image Signal Processing (ISP) which converts existing RGB images into RAW images has been studied. However, most existing methods require camera-specific metadata or paired RGB and RAW images to model the conversion, and they are not always available. In addition, there are issues in handling diverse ISPs and recovering global illumination. To tackle these limitations, we propose a self-supervised reversed ISP method that does not require metadata and paired images. The proposed method converts a RGB image into a RAW-like image taken in the same environment with the same sensor as a reference RAW image by dynamically selecting parameters of the reversed ISP pipeline based on the reference RAW image. The parameter selection is trained via pseudo paired data created from unpaired RGB and RAW images. We show that the proposed method is able to learn various reversed ISPs with comparable accuracy to other state-of-the-art supervised methods and convert unknown RGB images from COCO and Flickr1M to target RAW-like images more accurately in terms of pixel distribution. We also demonstrate that our generated RAW images improve performance on real RAW image object detection task.