# Pixel-Wise Color Constancy via Smoothness Techniques in Multi-Illuminant Scenes

arXiv: https://arxiv.org/abs/2402.02922 · HTML: https://mlsanity.com/paper/2402.02922/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 40 references that are in the map.
- First posted on arXiv 5 Feb 2024.

## Builds on (most cited first, 11 of 11)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Convolutional Color Constancy](https://mlsanity.com/paper/1507.00410/) (2015)
- [CLCC: Contrastive Learning for Color Constancy](https://mlsanity.com/paper/2106.04989/) (2021)
- [Conditional GANs for Multi-Illuminant Color Constancy: Revolution or Yet Another Approach?](https://mlsanity.com/paper/1811.06604/) (2018)
- [Single and Multiple Illuminant Estimation Using Convolutional Neural Networks](https://mlsanity.com/paper/1508.00998/) (2015)
- [Unsupervised Total Variation Loss for Semi-supervised Deep Learning of Semantic Segmentation](https://mlsanity.com/paper/1605.01368/) (2016)
- [Bag of Color Features For Color Constancy](https://mlsanity.com/paper/1906.04445/) (2019)
- [Color Constancy Convolutional Autoencoder](https://mlsanity.com/paper/1906.01340/) (2019)
- [MIMT: Multi-Illuminant Color Constancy via Multi-Task Local Surface and Light Color Learning](https://mlsanity.com/paper/2211.08772/) (2022)
- [Multi-color balance for color constancy](https://mlsanity.com/paper/2105.10228/) (2021)

## Built on by (most cited first, 3 of 3)

- [Multi-illuminant Color Constancy via Multi-scale Illuminant Estimation and Fusion](https://mlsanity.com/paper/2502.02021/) (2025)
- [Human-Aligned Evaluation of a Pixel-wise DNN Color Constancy Model](https://mlsanity.com/paper/2602.13887/) (2026)
- [SAFE: Scene-Aware Feature Modulation for Color Constancy with Learned Color Space in Pure-Color Scenes](https://mlsanity.com/paper/2608.13967/) (2026)

## Abstract (arXiv)

Most scenes are illuminated by several light sources, where the traditional assumption of uniform illumination is invalid. This issue is ignored in most color constancy methods, primarily due to the complex spatial impact of multiple light sources on the image. Moreover, most existing multi-illuminant methods fail to preserve the smooth change of illumination, which stems from spatial dependencies in natural images. Motivated by this, we propose a novel multi-illuminant color constancy method, by learning pixel-wise illumination maps caused by multiple light sources. The proposed method enforces smoothness within neighboring pixels, by regularizing the training with the total variation loss. Moreover, a bilateral filter is provisioned further to enhance the natural appearance of the estimated images, while preserving the edges. Additionally, we propose a label-smoothing technique that enables the model to generalize well despite the uncertainties in ground truth. Quantitative and qualitative experiments demonstrate that the proposed method outperforms the state-of-the-art.