STGV: Spatio-Temporal Hash Encoding for Gaussian-based Video Representation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910127379972096 |
|---|---|
| author | Lin, Jierun Chen, Jiacong Mao, Qingyu Liu, Shuai Meng, Xiandong Meng, Fanyang Liang, Yongsheng |
| author_facet | Lin, Jierun Chen, Jiacong Mao, Qingyu Liu, Shuai Meng, Xiandong Meng, Fanyang Liang, Yongsheng |
| contents | 2D Gaussian Splatting (2DGS) has recently become a promising paradigm for high-quality video representation. However, existing methods employ content-agnostic or spatio-temporal feature overlapping embeddings to predict canonical Gaussian primitive deformations, which entangles static and dynamic components in videos and prevents modeling their distinct properties effectively. These result in inaccurate predictions for spatio-temporal deformations and unsatisfactory representation quality. To address these problems, this paper proposes a Spatio-Temporal hash encoding framework for Gaussian-based Video representation (STGV). By decomposing video features into learnable 2D spatial and 3D temporal hash encodings, STGV effectively facilitates the learning of motion patterns for dynamic components while maintaining background details for static elements. In addition, we construct a more stable and consistent initial canonical Gaussian representation through a key frame canonical initialization strategy, preventing from feature overlapping and a structurally incoherent geometry representation. Experimental results demonstrate that our method attains better video representation quality (+0.98 PSNR) against other Gaussian-based methods and achieves competitive performance in downstream video tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_10910 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | STGV: Spatio-Temporal Hash Encoding for Gaussian-based Video Representation Lin, Jierun Chen, Jiacong Mao, Qingyu Liu, Shuai Meng, Xiandong Meng, Fanyang Liang, Yongsheng Computer Vision and Pattern Recognition 2D Gaussian Splatting (2DGS) has recently become a promising paradigm for high-quality video representation. However, existing methods employ content-agnostic or spatio-temporal feature overlapping embeddings to predict canonical Gaussian primitive deformations, which entangles static and dynamic components in videos and prevents modeling their distinct properties effectively. These result in inaccurate predictions for spatio-temporal deformations and unsatisfactory representation quality. To address these problems, this paper proposes a Spatio-Temporal hash encoding framework for Gaussian-based Video representation (STGV). By decomposing video features into learnable 2D spatial and 3D temporal hash encodings, STGV effectively facilitates the learning of motion patterns for dynamic components while maintaining background details for static elements. In addition, we construct a more stable and consistent initial canonical Gaussian representation through a key frame canonical initialization strategy, preventing from feature overlapping and a structurally incoherent geometry representation. Experimental results demonstrate that our method attains better video representation quality (+0.98 PSNR) against other Gaussian-based methods and achieves competitive performance in downstream video tasks. |
| title | STGV: Spatio-Temporal Hash Encoding for Gaussian-based Video Representation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.10910 |