DeepRAHT: Learning Predictive RAHT for Point Cloud Attribute Compression
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_ | 1866914263043407872 |
|---|---|
| author | Fu, Chunyang Qin, Tai Wang, Shiqi Li, Zhu |
| author_facet | Fu, Chunyang Qin, Tai Wang, Shiqi Li, Zhu |
| contents | Regional Adaptive Hierarchical Transform (RAHT) is an effective point cloud attribute compression (PCAC) method. However, its application in deep learning lacks research. In this paper, we propose an end-to-end RAHT framework for lossy PCAC based on the sparse tensor, called DeepRAHT. The RAHT transform is performed within the learning reconstruction process, without requiring manual RAHT for preprocessing. We also introduce the predictive RAHT to reduce bitrates and design a learning-based prediction model to enhance performance. Moreover, we devise a bitrate proxy that applies run-length coding to entropy model, achieving seamless variable-rate coding and improving robustness. DeepRAHT is a reversible and distortion-controllable framework, ensuring its lower bound performance and offering significant application potential. The experiments demonstrate that DeepRAHT is a high-performance, faster, and more robust solution than the baseline methods. Project Page: https://github.com/zb12138/DeepRAHT. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_12255 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DeepRAHT: Learning Predictive RAHT for Point Cloud Attribute Compression Fu, Chunyang Qin, Tai Wang, Shiqi Li, Zhu Image and Video Processing Computer Vision and Pattern Recognition Information Theory Multimedia Regional Adaptive Hierarchical Transform (RAHT) is an effective point cloud attribute compression (PCAC) method. However, its application in deep learning lacks research. In this paper, we propose an end-to-end RAHT framework for lossy PCAC based on the sparse tensor, called DeepRAHT. The RAHT transform is performed within the learning reconstruction process, without requiring manual RAHT for preprocessing. We also introduce the predictive RAHT to reduce bitrates and design a learning-based prediction model to enhance performance. Moreover, we devise a bitrate proxy that applies run-length coding to entropy model, achieving seamless variable-rate coding and improving robustness. DeepRAHT is a reversible and distortion-controllable framework, ensuring its lower bound performance and offering significant application potential. The experiments demonstrate that DeepRAHT is a high-performance, faster, and more robust solution than the baseline methods. Project Page: https://github.com/zb12138/DeepRAHT. |
| title | DeepRAHT: Learning Predictive RAHT for Point Cloud Attribute Compression |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Information Theory Multimedia |
| url | https://arxiv.org/abs/2601.12255 |