PRISM: Color-Stratified Point Cloud Sampling
For 3D reconstruction tasks, PRISM offers a novel sampling strategy that improves feature retention over conventional methods by leveraging color information.
PRISM introduces a color-guided stratified sampling method for RGB-LiDAR point clouds that allocates sampling density based on chromatic diversity, preserving texture-rich regions while reducing homogeneous surfaces. The method produces sparser point clouds that retain essential features for 3D reconstruction.
We present PRISM, a novel color-guided stratified sampling method for RGB-LiDAR point clouds. Our approach is motivated by the observation that unique scene features often exhibit chromatic diversity while repetitive, redundant features are homogeneous in color. Conventional downsampling methods (Random Sampling, Voxel Grid, Normal Space Sampling) enforce spatial uniformity while ignoring this photometric content. In contrast, PRISM allocates sampling density proportional to chromatic diversity. By treating RGB color space as the stratification domain and imposing a maximum capacity k per color bin, the method preserves texture-rich regions with high color variation while substantially reducing visually homogeneous surfaces. This shifts the sampling space from spatial coverage to visual complexity to produce sparser point clouds that retain essential features for 3D reconstruction tasks.