# CIE XYZ Net: Unprocessing Images for Low-Level Computer Vision Tasks

arXiv: https://arxiv.org/abs/2006.12709 · HTML: https://mlsanity.com/paper/2006.12709/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jun 2020.

## Built on by (most cited first, 29 of 29)

- [Invertible Image Signal Processing](https://mlsanity.com/paper/2103.15061/) (2021)
- [Model-Based Image Signal Processors via Learnable Dictionaries](https://mlsanity.com/paper/2201.03210/) (2022)
- [IDR: Self-Supervised Image Denoising via Iterative Data Refinement](https://mlsanity.com/paper/2111.14358/) (2021)
- [Towards Low Light Enhancement with RAW Images](https://mlsanity.com/paper/2112.14022/) (2021)
- [ParamISP: Learned Forward and Inverse ISPs using Camera Parameters](https://mlsanity.com/paper/2312.13313/) (2023)
- [Efficient Visual Computing with Camera RAW Snapshots](https://mlsanity.com/paper/2212.07778/) (2022)
- [Semi-Supervised Raw-to-Raw Mapping](https://mlsanity.com/paper/2106.13883/) (2021)
- [Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report](https://mlsanity.com/paper/2210.11153/) (2022)
- [Rawformer: Unpaired Raw-to-Raw Translation for Learnable Camera ISPs](https://mlsanity.com/paper/2404.10700/) (2024)
- [Pseudo-ISP: Learning Pseudo In-camera Signal Processing Pipeline from A Color Image Denoiser](https://mlsanity.com/paper/2103.10234/) (2021)
- [Removing Reflections from RAW Photos](https://mlsanity.com/paper/2404.14414/) (2024)
- [Time-Aware Auto White Balance in Mobile Photography](https://mlsanity.com/paper/2504.05623/) (2025)
- [RAW-Diffusion: RGB-Guided Diffusion Models for High-Fidelity RAW Image Generation](https://mlsanity.com/paper/2411.13150/) (2024)
- [CCMNet: Leveraging Calibrated Color Correction Matrices for Cross-Camera Color Constancy](https://mlsanity.com/paper/2504.07959/) (2025)
- [Self-Supervised Reversed Image Signal Processing via Reference-Guided Dynamic Parameter Selection](https://mlsanity.com/paper/2303.13916/) (2023)
- [Spectral Sensitivity Estimation Without a Camera](https://mlsanity.com/paper/2304.11549/) (2023)
- [A Learnable Color Correction Matrix for RAW Reconstruction](https://mlsanity.com/paper/2409.02497/) (2024)
- [Overexposure Mask Fusion: Generalizable Reverse ISP Multi-Step Refinement](https://mlsanity.com/paper/2210.11511/) (2022)
- [POS-ISP: Pipeline Optimization at the Sequence Level for Task-aware ISP](https://mlsanity.com/paper/2604.06938/) (2026)
- [Image color correction, enhancement, and editing](https://mlsanity.com/paper/2107.13117/) (2021)
- [RetouchUAA: Unconstrained Adversarial Attack via Image Retouching](https://mlsanity.com/paper/2311.16478/) (2023)
- [SEL-CIE: Knowledge-Guided Self-Supervised Learning Framework for CIE-XYZ Reconstruction from Non-Linear sRGB Images](https://mlsanity.com/paper/2405.12265/) (2024)
- [Uni-ISP: Toward Unifying the Learning of ISPs from Multiple Mobile Cameras](https://mlsanity.com/paper/2406.01003/) (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)
- [Learning Camera-Agnostic White-Balance Preferences](https://mlsanity.com/paper/2507.01342/) (2025)
- [Raw-JPEG Adapter: Efficient Raw Image Compression with JPEG](https://mlsanity.com/paper/2509.19624/) (2025)
- [Edit-aware RAW Reconstruction](https://mlsanity.com/paper/2512.05859/) (2025)
- [RAW-Domain Degradation Models for Realistic Smartphone Super-Resolution](https://mlsanity.com/paper/2603.12493/) (2026)
- [RawGen: Learning Camera Raw Image Generation](https://mlsanity.com/paper/2604.00093/) (2026)

## Abstract (arXiv)

Cameras currently allow access to two image states: (i) a minimally processed linear raw-RGB image state (i.e., raw sensor data) or (ii) a highly-processed nonlinear image state (e.g., sRGB). There are many computer vision tasks that work best with a linear image state, such as image deblurring and image dehazing. Unfortunately, the vast majority of images are saved in the nonlinear image state. Because of this, a number of methods have been proposed to "unprocess" nonlinear images back to a raw-RGB state. However, existing unprocessing methods have a drawback because raw-RGB images are sensor-specific. As a result, it is necessary to know which camera produced the sRGB output and use a method or network tailored for that sensor to properly unprocess it. This paper addresses this limitation by exploiting another camera image state that is not available as an output, but it is available inside the camera pipeline. In particular, cameras apply a colorimetric conversion step to convert the raw-RGB image to a device-independent space based on the CIE XYZ color space before they apply the nonlinear photo-finishing. Leveraging this canonical image state, we propose a deep learning framework, CIE XYZ Net, that can unprocess a nonlinear image back to the canonical CIE XYZ image. This image can then be processed by any low-level computer vision operator and re-rendered back to the nonlinear image. We demonstrate the usefulness of the CIE XYZ Net on several low-level vision tasks and show significant gains that can be obtained by this processing framework. Code and dataset are publicly available at https://github.com/mahmoudnafifi/CIE_XYZ_NET.