Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2402.01380 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929582591967232 |
|---|---|
| author | Zhang, Zhiyu Lu, Guo Liang, Huanxiong Tang, Anni Hu, Qiang Song, Li |
| author_facet | Zhang, Zhiyu Lu, Guo Liang, Huanxiong Tang, Anni Hu, Qiang Song, Li |
| contents | Volumetric videos, benefiting from immersive 3D realism and interactivity, hold vast potential for various applications, while the tremendous data volume poses significant challenges for compression. Recently, NeRF has demonstrated remarkable potential in volumetric video compression thanks to its simple representation and powerful 3D modeling capabilities, where a notable work is ReRF. However, ReRF separates the modeling from compression process, resulting in suboptimal compression efficiency. In contrast, in this paper, we propose a volumetric video compression method based on dynamic NeRF in a more compact manner. Specifically, we decompose the NeRF representation into the coefficient fields and the basis fields, incrementally updating the basis fields in the temporal domain to achieve dynamic modeling. Additionally, we perform end-to-end joint optimization on the modeling and compression process to further improve the compression efficiency. Extensive experiments demonstrate that our method achieves higher compression efficiency compared to ReRF on various datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_01380 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Efficient Dynamic-NeRF Based Volumetric Video Coding with Rate Distortion Optimization Zhang, Zhiyu Lu, Guo Liang, Huanxiong Tang, Anni Hu, Qiang Song, Li Computer Vision and Pattern Recognition Image and Video Processing Volumetric videos, benefiting from immersive 3D realism and interactivity, hold vast potential for various applications, while the tremendous data volume poses significant challenges for compression. Recently, NeRF has demonstrated remarkable potential in volumetric video compression thanks to its simple representation and powerful 3D modeling capabilities, where a notable work is ReRF. However, ReRF separates the modeling from compression process, resulting in suboptimal compression efficiency. In contrast, in this paper, we propose a volumetric video compression method based on dynamic NeRF in a more compact manner. Specifically, we decompose the NeRF representation into the coefficient fields and the basis fields, incrementally updating the basis fields in the temporal domain to achieve dynamic modeling. Additionally, we perform end-to-end joint optimization on the modeling and compression process to further improve the compression efficiency. Extensive experiments demonstrate that our method achieves higher compression efficiency compared to ReRF on various datasets. |
| title | Efficient Dynamic-NeRF Based Volumetric Video Coding with Rate Distortion Optimization |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2402.01380 |