Progressively Deformable 2D Gaussian Splatting for Video Representation at Arbitrary Resolutions
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_ | 1866914287979593728 |
|---|---|
| author | Liu, Mufan Yang, Qi Zhao, Miaoran Huang, He Yang, Le Li, Zhu Xu, Yiling |
| author_facet | Liu, Mufan Yang, Qi Zhao, Miaoran Huang, He Yang, Le Li, Zhu Xu, Yiling |
| contents | Implicit neural representations (INRs) enable fast video compression and effective video processing, but a single model rarely offers scalable decoding across rates and resolutions. In practice, multi-resolution typically relies on retraining or multi-branch designs, and structured pruning failed to provide a permutation-invariant progressive transmission order. Motivated by the explicit structure and efficiency of Gaussian splatting, we propose D2GV-AR, a deformable 2D Gaussian video representation that enables \emph{arbitrary-scale} rendering and \emph{any-ratio} progressive coding within a single model. We partition each video into fixed-length Groups of Pictures and represent each group with a canonical set of 2D Gaussian primitives, whose temporal evolution is modeled by a neural ordinary differential equation. During training and rendering, we apply scale-aware grouping according to Nyquist sampling theorem to form a nested hierarchy across resolutions. Once trained, primitives can be pruned via a D-optimal subset objective to enable any-ratio progressive coding. Extensive experiments show that D2GV-AR renders at over 250 FPS while matching or surpassing recent INR baselines, enabling multiscale continuous rate--quality adaptation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_05600 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Progressively Deformable 2D Gaussian Splatting for Video Representation at Arbitrary Resolutions Liu, Mufan Yang, Qi Zhao, Miaoran Huang, He Yang, Le Li, Zhu Xu, Yiling Computer Vision and Pattern Recognition Implicit neural representations (INRs) enable fast video compression and effective video processing, but a single model rarely offers scalable decoding across rates and resolutions. In practice, multi-resolution typically relies on retraining or multi-branch designs, and structured pruning failed to provide a permutation-invariant progressive transmission order. Motivated by the explicit structure and efficiency of Gaussian splatting, we propose D2GV-AR, a deformable 2D Gaussian video representation that enables \emph{arbitrary-scale} rendering and \emph{any-ratio} progressive coding within a single model. We partition each video into fixed-length Groups of Pictures and represent each group with a canonical set of 2D Gaussian primitives, whose temporal evolution is modeled by a neural ordinary differential equation. During training and rendering, we apply scale-aware grouping according to Nyquist sampling theorem to form a nested hierarchy across resolutions. Once trained, primitives can be pruned via a D-optimal subset objective to enable any-ratio progressive coding. Extensive experiments show that D2GV-AR renders at over 250 FPS while matching or surpassing recent INR baselines, enabling multiscale continuous rate--quality adaptation. |
| title | Progressively Deformable 2D Gaussian Splatting for Video Representation at Arbitrary Resolutions |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.05600 |