CVNov 22, 2021

Point Cloud Color Constancy

arXiv:2111.11280v25 citations
AI Analysis

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes