In this paper, we present Point Cloud Color Constancy, in short PCCC, an illumination chromaticity estimation algorithm exploiting a point cloud. We leverage the depth information captured by the time-of-flight (ToF) sensor mounted rigidly with the RGB sensor, and form a 6D cloud where each point contains the coordinates and RGB intensities, noted as (x,y,z,r,g,b). PCCC applies the PointNet architecture to the color constancy problem, deriving the illumination vector point-wise and then making a global decision about the global illumination chromaticity. On two popular RGB-D datasets, which we extend with illumination information, as well as on a novel benchmark, PCCC obtains lower error than the state-of-the-art algorithms. Our method is simple and fast, requiring merely 16*16-size input and reaching speed over 500 fps, including the cost of building the point cloud and net inference.
@article{arxiv.2111.11280,
title = {Point Cloud Color Constancy},
author = {Xiaoyan Xing and Yanlin Qian and Sibo Feng and Yuhan Dong and Jiri Matas},
journal= {arXiv preprint arXiv:2111.11280},
year = {2024}
}