# Unsupervised Learning for Color Constancy

arXiv: https://arxiv.org/abs/1712.00436 · HTML: https://mlsanity.com/paper/1712.00436/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Dec 2017.

## Built on by (most cited first, 19 of 19)

- [Auto White-Balance Correction for Mixed-Illuminant Scenes](https://mlsanity.com/paper/2109.08750/) (2021)
- [CCMNet: Leveraging Calibrated Color Correction Matrices for Cross-Camera Color Constancy](https://mlsanity.com/paper/2504.07959/) (2025)
- [Learning Enriched Illuminants for Cross and Single Sensor Color Constancy](https://mlsanity.com/paper/2203.11068/) (2022)
- [Modeling the Lighting in Scenes as Style for Auto White-Balance Correction](https://mlsanity.com/paper/2210.09090/) (2022)
- [GamutMLP: A Lightweight MLP for Color Loss Recovery](https://mlsanity.com/paper/2304.11743/) (2023)
- [Optimizing Illuminant Estimation in Dual-Exposure HDR Imaging](https://mlsanity.com/paper/2403.02449/) (2024)
- [Revisiting Image Fusion for Multi-Illuminant White-Balance Correction](https://mlsanity.com/paper/2503.14774/) (2025)
- [Generative Models for Multi-Illumination Color Constancy](https://mlsanity.com/paper/2109.00863/) (2021)
- [MIMT: Multi-Illuminant Color Constancy via Multi-Task Local Surface and Light Color Learning](https://mlsanity.com/paper/2211.08772/) (2022)
- [Deterministic Neural Illumination Mapping for Efficient Auto-White Balance Correction](https://mlsanity.com/paper/2308.03939/) (2023)
- [Zero-Shot Low Light Image Enhancement with Diffusion Prior](https://mlsanity.com/paper/2412.13401/) (2024)
- [Advancing Perception in Artificial Intelligence through Principles of Cognitive Science](https://mlsanity.com/paper/2310.08803/) (2023)
- [WB LUTs: Contrastive Learning for White Balancing Lookup Tables](https://mlsanity.com/paper/2404.10133/) (2024)
- [Image color correction, enhancement, and editing](https://mlsanity.com/paper/2107.13117/) (2021)
- [Primary visual cortex contributes to color constancy by predicting rather than discounting the illuminant: evidence from a computational study](https://mlsanity.com/paper/2412.07102/) (2024)
- [A Comprehensive Survey on Image Signal Processing Approaches for Low-Illumination Image Enhancement](https://mlsanity.com/paper/2502.05995/) (2025)
- [Boosting Illuminant Estimation in Deep Color Constancy through Enhancing Brightness Robustness](https://mlsanity.com/paper/2502.12418/) (2025)
- [Oneta: Multi-Style Image Enhancement Using Eigentransformation Functions](https://mlsanity.com/paper/2506.23547/) (2025)
- [Bio-inspired Color Constancy: From Gray Anchoring Theory to Gray Pixel Methods](https://mlsanity.com/paper/2604.20243/) (2026)

## Abstract (arXiv)

Most digital camera pipelines use color constancy methods to reduce the influence of illumination and camera sensor on the colors of scene objects. The highest accuracy of color correction is obtained with learning-based color constancy methods, but they require a significant amount of calibrated training images with known ground-truth illumination. Such calibration is time consuming, preferably done for each sensor individually, and therefore a major bottleneck in acquiring high color constancy accuracy. Statistics-based methods do not require calibrated training images, but they are less accurate. In this paper an unsupervised learning-based method is proposed that learns its parameter values after approximating the unknown ground-truth illumination of the training images, thus avoiding calibration. In terms of accuracy the proposed method outperforms all statistics-based and many learning-based methods. An extension of the method is also proposed, which learns the needed parameters from non-calibrated images taken with one sensor and which can then be successfully applied to images taken with another sensor. This effectively enables inter-camera unsupervised learning for color constancy. Additionally, a new high quality color constancy benchmark dataset with 1707 calibrated images is created, used for testing, and made publicly available. The results are presented and discussed. The source code and the dataset are available at http://www.fer.unizg.hr/ipg/resources/color_constancy/.