Learning Hierarchical Sparse Transform Coding for 3DGS Compression
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917289698263040 |
|---|---|
| author | Xu, Hao Wu, Xiaolin Zhang, Xi |
| author_facet | Xu, Hao Wu, Xiaolin Zhang, Xi |
| contents | Current 3DGS compression methods largely forego the neural analysis-synthesis transform, which is a crucial component in learned signal compression systems. As a result, redundancy removal is left solely to the entropy coder, overburdening the entropy coding module and reducing rate-distortion (R-D) performance. To fix this critical omission, we propose a training-time transform coding (TTC) method that adds the analysis-synthesis transform and optimizes it jointly with the 3DGS representation and entropy model. Concretely, we adopt a hierarchical design: a channel-wise KLT for decorrelation and energy compaction, followed by a sparsity-aware neural transform that reconstructs the KLT residuals with minimal parameter and computational overhead. Experiments show that our method delivers strong R-D performance with fast decoding, offering a favorable BD-rate-decoding-time trade-off over SOTA 3DGS compressors. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_22908 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning Hierarchical Sparse Transform Coding for 3DGS Compression Xu, Hao Wu, Xiaolin Zhang, Xi Computer Vision and Pattern Recognition Image and Video Processing Current 3DGS compression methods largely forego the neural analysis-synthesis transform, which is a crucial component in learned signal compression systems. As a result, redundancy removal is left solely to the entropy coder, overburdening the entropy coding module and reducing rate-distortion (R-D) performance. To fix this critical omission, we propose a training-time transform coding (TTC) method that adds the analysis-synthesis transform and optimizes it jointly with the 3DGS representation and entropy model. Concretely, we adopt a hierarchical design: a channel-wise KLT for decorrelation and energy compaction, followed by a sparsity-aware neural transform that reconstructs the KLT residuals with minimal parameter and computational overhead. Experiments show that our method delivers strong R-D performance with fast decoding, offering a favorable BD-rate-decoding-time trade-off over SOTA 3DGS compressors. |
| title | Learning Hierarchical Sparse Transform Coding for 3DGS Compression |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2505.22908 |