EHVC: Efficient Hierarchical Reference and Quality Structure for Neural Video Coding
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_ | 1866912570214973440 |
|---|---|
| author | Liao, Junqi Wu, Yaojun Lin, Chaoyi Deng, Zhipin Li, Li Liu, Dong Sun, Xiaoyan |
| author_facet | Liao, Junqi Wu, Yaojun Lin, Chaoyi Deng, Zhipin Li, Li Liu, Dong Sun, Xiaoyan |
| contents | Neural video codecs (NVCs), leveraging the power of end-to-end learning, have demonstrated remarkable coding efficiency improvements over traditional video codecs. Recent research has begun to pay attention to the quality structures in NVCs, optimizing them by introducing explicit hierarchical designs. However, less attention has been paid to the reference structure design, which fundamentally should be aligned with the hierarchical quality structure. In addition, there is still significant room for further optimization of the hierarchical quality structure. To address these challenges in NVCs, we propose EHVC, an efficient hierarchical neural video codec featuring three key innovations: (1) a hierarchical multi-reference scheme that draws on traditional video codec design to align reference and quality structures, thereby addressing the reference-quality mismatch; (2) a lookahead strategy to utilize an encoder-side context from future frames to enhance the quality structure; (3) a layer-wise quality scale with random quality training strategy to stabilize quality structures during inference. With these improvements, EHVC achieves significantly superior performance to the state-of-the-art NVCs. Code will be released in: https://github.com/bytedance/NEVC. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_04118 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EHVC: Efficient Hierarchical Reference and Quality Structure for Neural Video Coding Liao, Junqi Wu, Yaojun Lin, Chaoyi Deng, Zhipin Li, Li Liu, Dong Sun, Xiaoyan Image and Video Processing Artificial Intelligence Neural video codecs (NVCs), leveraging the power of end-to-end learning, have demonstrated remarkable coding efficiency improvements over traditional video codecs. Recent research has begun to pay attention to the quality structures in NVCs, optimizing them by introducing explicit hierarchical designs. However, less attention has been paid to the reference structure design, which fundamentally should be aligned with the hierarchical quality structure. In addition, there is still significant room for further optimization of the hierarchical quality structure. To address these challenges in NVCs, we propose EHVC, an efficient hierarchical neural video codec featuring three key innovations: (1) a hierarchical multi-reference scheme that draws on traditional video codec design to align reference and quality structures, thereby addressing the reference-quality mismatch; (2) a lookahead strategy to utilize an encoder-side context from future frames to enhance the quality structure; (3) a layer-wise quality scale with random quality training strategy to stabilize quality structures during inference. With these improvements, EHVC achieves significantly superior performance to the state-of-the-art NVCs. Code will be released in: https://github.com/bytedance/NEVC. |
| title | EHVC: Efficient Hierarchical Reference and Quality Structure for Neural Video Coding |
| topic | Image and Video Processing Artificial Intelligence |
| url | https://arxiv.org/abs/2509.04118 |