Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.17513 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915515837972480 |
|---|---|
| author | Zheng, Zihan Wu, Zhenlong Zhong, Houqiang Tian, Yuan Cao, Ning Xu, Lan Yao, Jiangchao Zhang, Xiaoyun Hu, Qiang Zhang, Wenjun |
| author_facet | Zheng, Zihan Wu, Zhenlong Zhong, Houqiang Tian, Yuan Cao, Ning Xu, Lan Yao, Jiangchao Zhang, Xiaoyun Hu, Qiang Zhang, Wenjun |
| contents | Achieving seamless viewing of high-fidelity volumetric video, comparable to 2D video experiences, remains an open challenge. Existing volumetric video compression methods either lack the flexibility to adjust quality and bitrate within a single model for efficient streaming across diverse networks and devices, or struggle with real-time decoding and rendering on lightweight mobile platforms. To address these challenges, we introduce 4DGCPro, a novel hierarchical 4D Gaussian compression framework that facilitates real-time mobile decoding and high-quality rendering via progressive volumetric video streaming in a single bitstream. Specifically, we propose a perceptually-weighted and compression-friendly hierarchical 4D Gaussian representation with motion-aware adaptive grouping to reduce temporal redundancy, preserve coherence, and enable scalable multi-level detail streaming. Furthermore, we present an end-to-end entropy-optimized training scheme, which incorporates layer-wise rate-distortion (RD) supervision and attribute-specific entropy modeling for efficient bitstream generation. Extensive experiments show that 4DGCPro enables flexible quality and multiple bitrate within a single model, achieving real-time decoding and rendering on mobile devices while outperforming existing methods in RD performance across multiple datasets. Project Page: https://mediax-sjtu.github.io/4DGCPro |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17513 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | 4DGCPro: Efficient Hierarchical 4D Gaussian Compression for Progressive Volumetric Video Streaming Zheng, Zihan Wu, Zhenlong Zhong, Houqiang Tian, Yuan Cao, Ning Xu, Lan Yao, Jiangchao Zhang, Xiaoyun Hu, Qiang Zhang, Wenjun Computer Vision and Pattern Recognition Achieving seamless viewing of high-fidelity volumetric video, comparable to 2D video experiences, remains an open challenge. Existing volumetric video compression methods either lack the flexibility to adjust quality and bitrate within a single model for efficient streaming across diverse networks and devices, or struggle with real-time decoding and rendering on lightweight mobile platforms. To address these challenges, we introduce 4DGCPro, a novel hierarchical 4D Gaussian compression framework that facilitates real-time mobile decoding and high-quality rendering via progressive volumetric video streaming in a single bitstream. Specifically, we propose a perceptually-weighted and compression-friendly hierarchical 4D Gaussian representation with motion-aware adaptive grouping to reduce temporal redundancy, preserve coherence, and enable scalable multi-level detail streaming. Furthermore, we present an end-to-end entropy-optimized training scheme, which incorporates layer-wise rate-distortion (RD) supervision and attribute-specific entropy modeling for efficient bitstream generation. Extensive experiments show that 4DGCPro enables flexible quality and multiple bitrate within a single model, achieving real-time decoding and rendering on mobile devices while outperforming existing methods in RD performance across multiple datasets. Project Page: https://mediax-sjtu.github.io/4DGCPro |
| title | 4DGCPro: Efficient Hierarchical 4D Gaussian Compression for Progressive Volumetric Video Streaming |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.17513 |