FANeRV: Frequency Separation and Augmentation based Neural Representation for Video
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915285596897280 |
|---|---|
| author | Yu, Li Li, Zhihui Yao, Chao Xiao, Jimin Gabbouj, Moncef |
| author_facet | Yu, Li Li, Zhihui Yao, Chao Xiao, Jimin Gabbouj, Moncef |
| contents | Neural representations for video (NeRV) have gained considerable attention for their strong performance across various video tasks. However, existing NeRV methods often struggle to capture fine spatial details, resulting in vague reconstructions. In this paper, we present a Frequency Separation and Augmentation based Neural Representation for video (FANeRV), which addresses these limitations with its core Wavelet Frequency Upgrade Block. This block explicitly separates input frames into high and low-frequency components using discrete wavelet transform, followed by targeted enhancement using specialized modules. Finally, a specially designed gated network effectively fuses these frequency components for optimal reconstruction. Additionally, convolutional residual enhancement blocks are integrated into the later stages of the network to balance parameter distribution and improve the restoration of high-frequency details. Experimental results demonstrate that FANeRV significantly improves reconstruction performance and excels in multiple tasks, including video compression, inpainting, and interpolation, outperforming existing NeRV methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_06755 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FANeRV: Frequency Separation and Augmentation based Neural Representation for Video Yu, Li Li, Zhihui Yao, Chao Xiao, Jimin Gabbouj, Moncef Computer Vision and Pattern Recognition Neural representations for video (NeRV) have gained considerable attention for their strong performance across various video tasks. However, existing NeRV methods often struggle to capture fine spatial details, resulting in vague reconstructions. In this paper, we present a Frequency Separation and Augmentation based Neural Representation for video (FANeRV), which addresses these limitations with its core Wavelet Frequency Upgrade Block. This block explicitly separates input frames into high and low-frequency components using discrete wavelet transform, followed by targeted enhancement using specialized modules. Finally, a specially designed gated network effectively fuses these frequency components for optimal reconstruction. Additionally, convolutional residual enhancement blocks are integrated into the later stages of the network to balance parameter distribution and improve the restoration of high-frequency details. Experimental results demonstrate that FANeRV significantly improves reconstruction performance and excels in multiple tasks, including video compression, inpainting, and interpolation, outperforming existing NeRV methods. |
| title | FANeRV: Frequency Separation and Augmentation based Neural Representation for Video |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.06755 |