A Multi-Hypothesis Classification Approach to Color Constancy

by   Daniel Hernandez-Juarez, et al.

Contemporary approaches frame the color constancy problem as learning camera specific illuminant mappings. While high accuracy can be achieved on camera specific data, these models depend on camera spectral sensitivity and typically exhibit poor generalisation to new devices. Additionally, regression methods produce point estimates that do not explicitly account for potential ambiguities among plausible illuminant solutions, due to the ill-posed nature of the problem. We propose a Bayesian framework that naturally handles color constancy ambiguity via a multi-hypothesis strategy. Firstly, we select a set of candidate scene illuminants in a data-driven fashion and apply them to a target image to generate of set of corrected images. Secondly, we estimate, for each corrected image, the likelihood of the light source being achromatic using a camera-agnostic CNN. Finally, our method explicitly learns a final illumination estimate from the generated posterior probability distribution. Our likelihood estimator learns to answer a camera-agnostic question and thus enables effective multi-camera training by disentangling illuminant estimation from the supervised learning task. We extensively evaluate our proposed approach and additionally set a benchmark for novel sensor generalisation without re-training. Our method provides state-of-the-art accuracy on multiple public datasets (up to 11 real-time execution.


page 1

page 3

page 8

page 14

page 16

page 17


A Multi-Hypothesis Approach to Color Constancy

Contemporary approaches frame the color constancy problem as learning ca...

Meta-Learning for Few-shot Camera-Adaptive Color Constancy

Digital camera pipelines employ color constancy methods to estimate an u...

Cross-Camera Convolutional Color Constancy

We present "Cross-Camera Convolutional Color Constancy" (C5), a learning...

Dichromatic Gray Pixel for Camera-agnostic Color Constancy

We propose a novel statistical color constancy method, especially suitab...

Improving Color Constancy by Discounting the Variation of Camera Spectral Sensitivity

It is an ill-posed problem to recover the true scene colors from a color...

A Benchmark for Temporal Color Constancy

Temporal Color Constancy (CC) is a recently proposed approach that chall...

Code Repositories


[CVPR2020] A Multi-Hypothesis Approach to Color Constancy

view repo

Please sign up or login with your details

Forgot password? Click here to reset