mlsanityData to 14 Oct 2026

ROI-Guided Point Cloud Geometry Compression Towards Human and Machine Vision

arXiv 2504.14240 ↗First posted 19 Apr 2025cs.CV cs.MMcited by 4

Not on the map. Why?

Abstract (arXiv)

Point cloud data is pivotal in applications like autonomous driving, virtual reality, and robotics. However, its substantial volume poses significant challenges in storage and transmission. In order to obtain a high compression ratio, crucial semantic details usually confront severe damage, leading to difficulties in guaranteeing the accuracy of downstream tasks. To tackle this problem, we are the first to introduce a novel Region of Interest (ROI)-guided Point Cloud Geometry Compression (RPCGC) method for human and machine vision. Our framework employs a dual-branch parallel structure, where the base layer encodes and decodes a simplified version of the point cloud, and the enhancement layer refines this by focusing on geometry details. Furthermore, the residual information of the enhancement layer undergoes refinement through an ROI prediction network. This network generates mask information, which is then incorporated into the residuals, serving as a strong supervision signal. Additionally, we intricately apply these mask details in the Rate-Distortion (RD) optimization process, with each point weighted in the distortion calculation. Our loss function includes RD loss and detection loss to better guide point cloud encoding for the machine. Experiment results demonstrate that RPCGC achieves exceptional compression performance and better detection accuracy (10% gain) than some learning-based compression methods at high bitrates in ScanNet and SUN RGB-D datasets.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 26 of its 52 references that are in the map. First posted on arXiv 19 Apr 2025.

Builds on

26 of 52 references.

References · 26

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  5. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  6. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  7. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 979
  8. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  9. 2020Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modulescited by 590
  10. 2021Group-Free 3D Object Detection via Transformerscited by 215
  11. 2020Multiscale Point Cloud Geometry Compressioncited by 74
  12. 2020OctSqueeze: Octree-Structured Entropy Model for LiDAR Compressioncited by 73
14 more
  1. 2021Sparse Tensor-based Multiscale Representation for Point Cloud Geometry Compressioncited by 70
  2. 2021VoxelContext-Net: An Octree based Framework for Point Cloud Compressioncited by 61
  3. 2019Learned Point Cloud Geometry Compressioncited by 58
  4. 2019Learning Convolutional Transforms for Lossy Point Cloud Geometry Compressioncited by 54
  5. 2020Improved Deep Point Cloud Geometry Compressioncited by 43
  6. 2019Deep AutoEncoder-based Lossy Geometry Compression for Point Cloudscited by 29
  7. 2021Towards End-to-End Image Compression and Analysis with Transformerscited by 26
  8. 2023Lossless Point Cloud Geometry and Attribute Compression Using a Learned Conditional Probability Modelcited by 25
  9. 2022GRASP-Net: Geometric Residual Analysis and Synthesis for Point Cloud Compressioncited by 17
  10. 2020A generalized Hausdorff distance based quality metric for point cloud geometrycited by 15
  11. 2016Semantic Perceptual Image Compression using Deep Convolution Networkscited by 12
  12. 2021Video Coding for Machine: Compact Visual Representation Compression for Intelligent Collaborative Analyticscited by 11
  13. 2022Learning-based Lossless Point Cloud Geometry Coding using Sparse Tensorscited by 8
  14. 2023Learned Point Cloud Compression for Classificationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025Point Cloud Compression and Objective Quality Assessment: A Surveycited by 1
  2. 2026Overview and Comparison of AVS Point Cloud Compression Standardcited by 1
  3. 2025Bidirectional Feature-aligned Motion Transformation for Efficient Dynamic Point Cloud Compressioncited by 0
  4. 2026TAFA-GSGC: Group-wise Scalable Point Cloud Geometry Compression with Progressive Residual Refinementcited by 0