PRISM: Color-Stratified Point Cloud Sampling
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914533094719488 |
|---|---|
| author | Lim, Hansol Im, Minhyeok Choi, Jongseong Brad |
| author_facet | Lim, Hansol Im, Minhyeok Choi, Jongseong Brad |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_06839 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PRISM: Color-Stratified Point Cloud Sampling Lim, Hansol Im, Minhyeok Choi, Jongseong Brad Computer Vision and Pattern Recognition 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. |
| title | PRISM: Color-Stratified Point Cloud Sampling |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.06839 |