CAT-3DGS Pro: A New Benchmark for Efficient 3DGS Compression
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916653973897216 |
|---|---|
| author | Zhan, Yu-Ting Yang, He-bi Ho, Cheng-Yuan Chiang, Jui-Chiu Peng, Wen-Hsiao |
| author_facet | Zhan, Yu-Ting Yang, He-bi Ho, Cheng-Yuan Chiang, Jui-Chiu Peng, Wen-Hsiao |
| contents | 3D Gaussian Splatting (3DGS) has shown immense potential for novel view synthesis. However, achieving rate-distortion-optimized compression of 3DGS representations for transmission and/or storage applications remains a challenge. CAT-3DGS introduces a context-adaptive triplane hyperprior for end-to-end optimized compression, delivering state-of-the-art coding performance. Despite this, it requires prolonged training and decoding time. To address these limitations, we propose CAT-3DGS Pro, an enhanced version of CAT-3DGS that improves both compression performance and computational efficiency. First, we introduce a PCA-guided vector-matrix hyperprior, which replaces the triplane-based hyperprior to reduce redundant parameters. To achieve a more balanced rate-distortion trade-off and faster encoding, we propose an alternate optimization strategy (A-RDO). Additionally, we refine the sampling rate optimization method in CAT-3DGS, leading to significant improvements in rate-distortion performance. These enhancements result in a 46.6% BD-rate reduction and 3x speedup in training time on BungeeNeRF, while achieving 5x acceleration in decoding speed for the Amsterdam scene compared to CAT-3DGS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_12862 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CAT-3DGS Pro: A New Benchmark for Efficient 3DGS Compression Zhan, Yu-Ting Yang, He-bi Ho, Cheng-Yuan Chiang, Jui-Chiu Peng, Wen-Hsiao Computer Vision and Pattern Recognition 3D Gaussian Splatting (3DGS) has shown immense potential for novel view synthesis. However, achieving rate-distortion-optimized compression of 3DGS representations for transmission and/or storage applications remains a challenge. CAT-3DGS introduces a context-adaptive triplane hyperprior for end-to-end optimized compression, delivering state-of-the-art coding performance. Despite this, it requires prolonged training and decoding time. To address these limitations, we propose CAT-3DGS Pro, an enhanced version of CAT-3DGS that improves both compression performance and computational efficiency. First, we introduce a PCA-guided vector-matrix hyperprior, which replaces the triplane-based hyperprior to reduce redundant parameters. To achieve a more balanced rate-distortion trade-off and faster encoding, we propose an alternate optimization strategy (A-RDO). Additionally, we refine the sampling rate optimization method in CAT-3DGS, leading to significant improvements in rate-distortion performance. These enhancements result in a 46.6% BD-rate reduction and 3x speedup in training time on BungeeNeRF, while achieving 5x acceleration in decoding speed for the Amsterdam scene compared to CAT-3DGS. |
| title | CAT-3DGS Pro: A New Benchmark for Efficient 3DGS Compression |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.12862 |