Exploring Histogram-based Color Constancy


David R. Treadwell IV (Northeastern University), Yunxuan Rao (Northeastern University), Daniel Y. Bi (Northeastern University), Bruce A. Maxwell (Northeastern University)
The 35th British Machine Vision Conference
PDFPosterVideo (Right click to download)

Abstract

We present a lightweight fully convolutional network for color constancy (LHCC). The network uses multiple 2-D projections of the 3-D log RGB histogram of an image in order to predict the color correction coefficients. In developing the network, we explored whether to use linear RGB or log RGB data, the network structure (width and depth), how to handle dark pixels, how to generate the 2-D mappings of the 3-D histogram, and how to normalize or transform the bin counts in order to preserve the fine histogram structure. Our results show that attention to each of these details makes a difference in overall performance. Our most significant findings are that using log RGB outperforms linear RGB for this task, and that using a log transformation of the bin counts outperforms thresholding, a hyperbolic tangent, and linear normalization. Our exploration resulted in a fully convolutional network with 0.5M parameters that sets a new performance standard on SimpleCube++ with a surprising $2.72^{\circ}$ angular error on the worst 25\%. It is also competitive on older data sets such as Gehler-Shi and NUS-8.

Citation

@inproceedings{IV_2025_BMVC,
author    = {David R. Treadwell IV and Yunxuan Rao and Daniel Y. Bi and Bruce A. Maxwell},
title     = {Exploring Histogram-based Color Constancy},
booktitle = {36th British Machine Vision Conference 2025, {BMVC} 2025, Sheffield, UK, November 24-27, 2025},
publisher = {BMVA},
year      = {2025},
url       = {https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_404/paper.pdf}
}


Copyright © 2025 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection