# CameraNet: A Two-Stage Framework for Effective Camera ISP Learning

arXiv: https://arxiv.org/abs/1908.01481 · HTML: https://mlsanity.com/paper/1908.01481/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Aug 2019.

## Built on by (most cited first, 30 of 38)

- [Invertible Image Signal Processing](https://mlsanity.com/paper/2103.15061/) (2021)
- [Learning RAW-to-sRGB Mappings with Inaccurately Aligned Supervision](https://mlsanity.com/paper/2108.08119/) (2021)
- [Model-Based Image Signal Processors via Learnable Dictionaries](https://mlsanity.com/paper/2201.03210/) (2022)
- [4D LUT: Learnable Context-Aware 4D Lookup Table for Image Enhancement](https://mlsanity.com/paper/2209.01749/) (2022)
- [NILUT: Conditional Neural Implicit 3D Lookup Tables for Image Enhancement](https://mlsanity.com/paper/2306.11920/) (2023)
- [Beyond Joint Demosaicking and Denoising: An Image Processing Pipeline for a Pixel-bin Image Sensor](https://mlsanity.com/paper/2104.09398/) (2021)
- [GenISP: Neural ISP for Low-Light Machine Cognition](https://mlsanity.com/paper/2205.03688/) (2022)
- [RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images](https://mlsanity.com/paper/2408.14802/) (2024)
- [Semi-Supervised Raw-to-Raw Mapping](https://mlsanity.com/paper/2106.13883/) (2021)
- [Enhancing RAW-to-sRGB with Decoupled Style Structure in Fourier Domain](https://mlsanity.com/paper/2401.02161/) (2024)
- [BSRAW: Improving Blind RAW Image Super-Resolution](https://mlsanity.com/paper/2312.15487/) (2023)
- [Rawformer: Unpaired Raw-to-Raw Translation for Learnable Camera ISPs](https://mlsanity.com/paper/2404.10700/) (2024)
- [DemosaicFormer: Coarse-to-Fine Demosaicing Network for HybridEVS Camera](https://mlsanity.com/paper/2406.07951/) (2024)
- [Computational Optics for Mobile Terminals in Mass Production](https://mlsanity.com/paper/2305.05886/) (2023)
- [DRAW: Defending Camera-shooted RAW against Image Manipulation](https://mlsanity.com/paper/2307.16418/) (2023)
- [RViDeformer: Efficient Raw Video Denoising Transformer with a Larger Benchmark Dataset](https://mlsanity.com/paper/2305.00767/) (2023)
- [Learning to See Low-Light Images via Feature Domain Adaptation](https://mlsanity.com/paper/2312.06723/) (2023)
- [RAW-Diffusion: RGB-Guided Diffusion Models for High-Fidelity RAW Image Generation](https://mlsanity.com/paper/2411.13150/) (2024)
- [All You Need is RAW: Defending Against Adversarial Attacks with Camera Image Pipelines](https://mlsanity.com/paper/2112.09219/) (2021)
- [DRL-ISP: Multi-Objective Camera ISP with Deep Reinforcement Learning](https://mlsanity.com/paper/2207.03081/) (2022)
- [Del-Net: A Single-Stage Network for Mobile Camera ISP](https://mlsanity.com/paper/2108.01623/) (2021)
- [LDM-ISP: Enhancing Neural ISP for Low Light with Latent Diffusion Models](https://mlsanity.com/paper/2312.01027/) (2023)
- [An End-to-End Real-World Camera Imaging Pipeline](https://mlsanity.com/paper/2411.10773/) (2024)
- [PyNET-QxQ: An Efficient PyNET Variant for QxQ Bayer Pattern Demosaicing in CMOS Image Sensors](https://mlsanity.com/paper/2203.04314/) (2022)
- [PQDynamicISP: Dynamically Controlled Image Signal Processor for Any Image Sensors Pursuing Perceptual Quality](https://mlsanity.com/paper/2403.10091/) (2024)
- [Simple Image Signal Processing using Global Context Guidance](https://mlsanity.com/paper/2404.11569/) (2024)
- [RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images and A Benchmark](https://mlsanity.com/paper/2503.17027/) (2025)
- [Improved Mapping Between Illuminations and Sensors for RAW Images](https://mlsanity.com/paper/2508.14730/) (2025)
- [Task-Aware Image Signal Processor for Advanced Visual Perception](https://mlsanity.com/paper/2509.13762/) (2025)
- [CRISPnet: Color Rendition ISP Net](https://mlsanity.com/paper/2203.10562/) (2022)

## Abstract (arXiv)

Traditional image signal processing (ISP) pipeline consists of a set of individual image processing components onboard a camera to reconstruct a high-quality sRGB image from the sensor raw data. Due to the hand-crafted nature of the ISP components, traditional ISP pipeline has limited reconstruction quality under challenging scenes. Recently, the convolutional neural networks (CNNs) have demonstrated their competitiveness in solving many individual image processing problems, such as image denoising, demosaicking, white balance and contrast enhancement. However, it remains a question whether a CNN model can address the multiple tasks inside an ISP pipeline simultaneously. We make a good attempt along this line and propose a novel framework, which we call CameraNet, for effective and general ISP pipeline learning. The CameraNet is composed of two CNN modules to account for two sets of relatively uncorrelated subtasks in an ISP pipeline: restoration and enhancement. To train the two-stage CameraNet model, we specify two groundtruths that can be easily created in the common workflow of photography. CameraNet is trained to progressively address the restoration and the enhancement subtasks with its two modules. Experiments show that the proposed CameraNet achieves consistently compelling reconstruction quality on three benchmark datasets and outperforms traditional ISP pipelines.