A Neural-network Enhanced Video Coding Framework beyond ECM
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909114454507520 |
|---|---|
| author | Zhao, Yanchen He, Wenxuan Jia, Chuanmin Wang, Qizhe Li, Junru Li, Yue Lin, Chaoyi Zhang, Kai Zhang, Li Ma, Siwei |
| author_facet | Zhao, Yanchen He, Wenxuan Jia, Chuanmin Wang, Qizhe Li, Junru Li, Yue Lin, Chaoyi Zhang, Kai Zhang, Li Ma, Siwei |
| contents | In this paper, a hybrid video compression framework is proposed that serves as a demonstrative showcase of deep learning-based approaches extending beyond the confines of traditional coding methodologies. The proposed hybrid framework is founded upon the Enhanced Compression Model (ECM), which is a further enhancement of the Versatile Video Coding (VVC) standard. We have augmented the latest ECM reference software with well-designed coding techniques, including block partitioning, deep learning-based loop filter, and the activation of block importance mapping (BIM) which was integrated but previously inactive within ECM, further enhancing coding performance. Compared with ECM-10.0, our method achieves 6.26, 13.33, and 12.33 BD-rate savings for the Y, U, and V components under random access (RA) configuration, respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_08397 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Neural-network Enhanced Video Coding Framework beyond ECM Zhao, Yanchen He, Wenxuan Jia, Chuanmin Wang, Qizhe Li, Junru Li, Yue Lin, Chaoyi Zhang, Kai Zhang, Li Ma, Siwei Computer Vision and Pattern Recognition In this paper, a hybrid video compression framework is proposed that serves as a demonstrative showcase of deep learning-based approaches extending beyond the confines of traditional coding methodologies. The proposed hybrid framework is founded upon the Enhanced Compression Model (ECM), which is a further enhancement of the Versatile Video Coding (VVC) standard. We have augmented the latest ECM reference software with well-designed coding techniques, including block partitioning, deep learning-based loop filter, and the activation of block importance mapping (BIM) which was integrated but previously inactive within ECM, further enhancing coding performance. Compared with ECM-10.0, our method achieves 6.26, 13.33, and 12.33 BD-rate savings for the Y, U, and V components under random access (RA) configuration, respectively. |
| title | A Neural-network Enhanced Video Coding Framework beyond ECM |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.08397 |