Tree-NeRV: A Tree-Structured Neural Representation for Efficient Non-Uniform Video Encoding
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917988586749952 |
|---|---|
| author | Zhao, Jiancheng Zhan, Yifan Zhu, Qingtian Ma, Mingze Niu, Muyao Wan, Zunian Ji, Xiang Zheng, Yinqiang |
| author_facet | Zhao, Jiancheng Zhan, Yifan Zhu, Qingtian Ma, Mingze Niu, Muyao Wan, Zunian Ji, Xiang Zheng, Yinqiang |
| contents | Implicit Neural Representations for Videos (NeRV) have emerged as a powerful paradigm for video representation, enabling direct mappings from frame indices to video frames. However, existing NeRV-based methods do not fully exploit temporal redundancy, as they rely on uniform sampling along the temporal axis, leading to suboptimal rate-distortion (RD) performance. To address this limitation, we propose Tree-NeRV, a novel tree-structured feature representation for efficient and adaptive video encoding. Unlike conventional approaches, Tree-NeRV organizes feature representations within a Binary Search Tree (BST), enabling non-uniform sampling along the temporal axis. Additionally, we introduce an optimization-driven sampling strategy, dynamically allocating higher sampling density to regions with greater temporal variation. Extensive experiments demonstrate that Tree-NeRV achieves superior compression efficiency and reconstruction quality, outperforming prior uniform sampling-based methods. Code will be released. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_12899 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Tree-NeRV: A Tree-Structured Neural Representation for Efficient Non-Uniform Video Encoding Zhao, Jiancheng Zhan, Yifan Zhu, Qingtian Ma, Mingze Niu, Muyao Wan, Zunian Ji, Xiang Zheng, Yinqiang Computer Vision and Pattern Recognition Implicit Neural Representations for Videos (NeRV) have emerged as a powerful paradigm for video representation, enabling direct mappings from frame indices to video frames. However, existing NeRV-based methods do not fully exploit temporal redundancy, as they rely on uniform sampling along the temporal axis, leading to suboptimal rate-distortion (RD) performance. To address this limitation, we propose Tree-NeRV, a novel tree-structured feature representation for efficient and adaptive video encoding. Unlike conventional approaches, Tree-NeRV organizes feature representations within a Binary Search Tree (BST), enabling non-uniform sampling along the temporal axis. Additionally, we introduce an optimization-driven sampling strategy, dynamically allocating higher sampling density to regions with greater temporal variation. Extensive experiments demonstrate that Tree-NeRV achieves superior compression efficiency and reconstruction quality, outperforming prior uniform sampling-based methods. Code will be released. |
| title | Tree-NeRV: A Tree-Structured Neural Representation for Efficient Non-Uniform Video Encoding |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.12899 |