mlsanityData to 7 Oct 2026

PRISM: Color-Stratified Point Cloud Sampling

arXiv 2601.06839 ↗First posted 11 Jan 2026cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 20 of its 36 references that are in the map. First posted on arXiv 11 Jan 2026.

Builds on

20 of 36 references.

References · 20

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  2. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  3. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  4. 2022DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detectioncited by 224
  5. 2020Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadwayscited by 77
  6. 2019SampleNet: Differentiable Point Cloud Samplingcited by 74
  7. 2023LiDAR-NeRF: Novel LiDAR View Synthesis via Neural Radiance Fieldscited by 46
  8. 2021Paris-CARLA-3D: A Real and Synthetic Outdoor Point Cloud Dataset for Challenging Tasks in 3D Mappingcited by 25
  9. 2024GauU-Scene: A Scene Reconstruction Benchmark on Large Scale 3D Reconstruction Dataset Using Gaussian Splattingcited by 15
  10. 2025SAMFusion: Sensor-Adaptive Multimodal Fusion for 3D Object Detection in Adverse Weathercited by 10
  11. 2019LiDAR Enhanced Structure-from-Motioncited by 6
  12. 2024LiDAR-3DGS: LiDAR Reinforced 3D Gaussian Splatting for Multimodal Radiance Field Renderingcited by 6
8 more
  1. 2025LiDAR-VGGT: Cross-Modal Coarse-to-Fine Fusion for Globally Consistent and Metric-Scale Dense Mappingcited by 4
  2. 2025IDSplat: Instance-Decomposed 3D Gaussian Splatting for Driving Scenescited by 3
  3. 2025UAV-MM3D: A Large-Scale Synthetic Benchmark for 3D Perception of Unmanned Aerial Vehicles with Multi-Modal Datacited by 3
  4. 2025Robust and High-Fidelity 3D Gaussian Splatting: Fusing Pose Priors and Geometry Constraints for Texture-Deficient Outdoor Scenescited by 2
  5. 2025LiDAR-GS++:Improving LiDAR Gaussian Reconstruction via Diffusion Priorscited by 2
  6. 2022APSNet: Attention Based Point Cloud Samplingcited by 1
  7. 2025DensifyBeforehand: LiDAR-assisted Content-aware Densification for Efficient and Quality 3D Gaussian Splattingcited by 1
  8. 2025SurfFill: Completion of LiDAR Point Clouds via Gaussian Surfel Splattingcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Transforming Omnidirectional RGB-LiDAR data into 3D Gaussian Splattingcited by 0