Frequency-aware Neural Representation for Videos
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914277902778368 |
|---|---|
| author | Zhu, Jun Zhang, Xinfeng Tang, Lv Jiang, Junhao Zhang, Gai Wang, Jia |
| author_facet | Zhu, Jun Zhang, Xinfeng Tang, Lv Jiang, Junhao Zhang, Gai Wang, Jia |
| contents | Implicit Neural Representations (INRs) have emerged as a promising paradigm for video compression. However, existing INR-based frameworks typically suffer from inherent spectral bias, which favors low-frequency components and leads to over-smoothed reconstructions and suboptimal rate-distortion performance. In this paper, we propose FaNeRV, a Frequency-aware Neural Representation for videos, which explicitly decouples low- and high-frequency components to enable efficient and faithful video reconstruction. FaNeRV introduces a multi-resolution supervision strategy that guides the network to progressively capture global structures and fine-grained textures through staged supervision . To further enhance high-frequency reconstruction, we propose a dynamic high-frequency injection mechanism that adaptively emphasizes challenging regions. In addition, we design a frequency-decomposed network module to improve feature modeling across different spectral bands. Extensive experiments on standard benchmarks demonstrate that FaNeRV significantly outperforms state-of-the-art INR methods and achieves competitive rate-distortion performance against traditional codecs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_17741 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Frequency-aware Neural Representation for Videos Zhu, Jun Zhang, Xinfeng Tang, Lv Jiang, Junhao Zhang, Gai Wang, Jia Computer Vision and Pattern Recognition Implicit Neural Representations (INRs) have emerged as a promising paradigm for video compression. However, existing INR-based frameworks typically suffer from inherent spectral bias, which favors low-frequency components and leads to over-smoothed reconstructions and suboptimal rate-distortion performance. In this paper, we propose FaNeRV, a Frequency-aware Neural Representation for videos, which explicitly decouples low- and high-frequency components to enable efficient and faithful video reconstruction. FaNeRV introduces a multi-resolution supervision strategy that guides the network to progressively capture global structures and fine-grained textures through staged supervision . To further enhance high-frequency reconstruction, we propose a dynamic high-frequency injection mechanism that adaptively emphasizes challenging regions. In addition, we design a frequency-decomposed network module to improve feature modeling across different spectral bands. Extensive experiments on standard benchmarks demonstrate that FaNeRV significantly outperforms state-of-the-art INR methods and achieves competitive rate-distortion performance against traditional codecs. |
| title | Frequency-aware Neural Representation for Videos |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.17741 |