Point Cloud Color Constancy
This addresses color constancy in computer vision for applications like robotics and photography, but it is incremental as it adapts an existing architecture to a new data type.
The paper tackles illumination chromaticity estimation by using a point cloud with depth and RGB data, applying PointNet to derive illumination vectors and achieving lower error than state-of-the-art on extended and new benchmarks, with speeds over 500 fps.
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.