RAVE: Rate-Adaptive Visual Encoding for 3D Gaussian Splatting
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917229840302080 |
|---|---|
| author | Tran, Hoang-Nhat Di Sario, Francesco Spadaro, Gabriele Valenzise, Giuseppe Tartaglione, Enzo |
| author_facet | Tran, Hoang-Nhat Di Sario, Francesco Spadaro, Gabriele Valenzise, Giuseppe Tartaglione, Enzo |
| contents | Recent advances in neural scene representations have transformed immersive multimedia, with 3D Gaussian Splatting (3DGS) enabling real-time photorealistic rendering. Despite its efficiency, 3DGS suffers from large memory requirements and costly training procedures, motivating efforts toward compression. Existing approaches, however, operate at fixed rates, limiting adaptability to varying bandwidth and device constraints. In this work, we propose a flexible compression scheme for 3DGS that supports interpolation at any rate between predefined bounds. Our method is computationally lightweight, requires no retraining for any rate, and preserves rendering quality across a broad range of operating points. Experiments demonstrate that the approach achieves efficient, high-quality compression while offering dynamic rate control, making it suitable for practical deployment in immersive applications. The code is available at https://github.com/inspiros/RAVE. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_07052 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RAVE: Rate-Adaptive Visual Encoding for 3D Gaussian Splatting Tran, Hoang-Nhat Di Sario, Francesco Spadaro, Gabriele Valenzise, Giuseppe Tartaglione, Enzo Computer Vision and Pattern Recognition Recent advances in neural scene representations have transformed immersive multimedia, with 3D Gaussian Splatting (3DGS) enabling real-time photorealistic rendering. Despite its efficiency, 3DGS suffers from large memory requirements and costly training procedures, motivating efforts toward compression. Existing approaches, however, operate at fixed rates, limiting adaptability to varying bandwidth and device constraints. In this work, we propose a flexible compression scheme for 3DGS that supports interpolation at any rate between predefined bounds. Our method is computationally lightweight, requires no retraining for any rate, and preserves rendering quality across a broad range of operating points. Experiments demonstrate that the approach achieves efficient, high-quality compression while offering dynamic rate control, making it suitable for practical deployment in immersive applications. The code is available at https://github.com/inspiros/RAVE. |
| title | RAVE: Rate-Adaptive Visual Encoding for 3D Gaussian Splatting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.07052 |