V^3: Viewing Volumetric Videos on Mobiles via Streamable 2D Dynamic Gaussians
Uložené v:
| Názov: | V^3: Viewing Volumetric Videos on Mobiles via Streamable 2D Dynamic Gaussians |
|---|---|
| Autori: | Penghao Wang, Zhirui Zhang, Liao Wang, Kaixin Yao, Siyuan Xie, Jingyi Yu, Minye Wu, Lan Xu |
| Zdroj: | ACM Transactions on Graphics. 43:1-13 |
| Publication Status: | Preprint |
| Informácie o vydavateľovi: | Association for Computing Machinery (ACM), 2024. |
| Rok vydania: | 2024 |
| Predmety: | volumetric video, FOS: Computer and information sciences, Technology, REPRESENTATION, Science & Technology, human performance, Computer Vision and Pattern Recognition (cs.CV), RADIANCE FIELDS, Computer Science - Computer Vision and Pattern Recognition, Software Engineering, 02 engineering and technology, 4607 Graphics, augmented reality and games, Computer Science, Software Engineering, mobile rendering, Graphics (cs.GR), Computer Science - Graphics, 0806 Information Systems, Computer Science, 0801 Artificial Intelligence and Image Processing, 0202 electrical engineering, electronic engineering, information engineering, Neural rendering, 3D Gaussian Splatting |
| Popis: | Experiencing high-fidelity volumetric video as seamlessly as 2D videos is a long-held dream. However, current dynamic 3DGS methods, despite their high rendering quality, face challenges in streaming on mobile devices due to computational and bandwidth constraints. In this paper, we introduce V 3 (Viewing Volumetric Videos), a novel approach that enables high-quality mobile rendering through the streaming of dynamic Gaussians. Our key innovation is to view dynamic 3DGS as 2D videos, facilitating the use of hardware video codecs. Additionally, we propose a two-stage training strategy to reduce storage requirements with rapid training speed. The first stage employs hash encoding and shallow MLP to learn motion, then reduces the number of Gaussians through pruning to meet the streaming requirements, while the second stage fine tunes other Gaussian attributes using residual entropy loss and temporal loss to improve temporal continuity. This strategy, which disentangles motion and appearance, maintains high rendering quality with compact storage requirements. Meanwhile, we designed a multi-platform player to decode and render 2D Gaussian videos. Extensive experiments demonstrate the effectiveness of V 3 , outperforming other methods by enabling high-quality rendering and streaming on common devices, which is unseen before. As the first to stream dynamic Gaussians on mobile devices, our companion player offers users an unprecedented volumetric video experience, including smooth scrolling and instant sharing. Our project page with source code is available at https://authoritywang.github.io/v3/. |
| Druh dokumentu: | Article |
| Jazyk: | English |
| ISSN: | 1557-7368 0730-0301 |
| DOI: | 10.1145/3687935 |
| DOI: | 10.48550/arxiv.2409.13648 |
| Prístupová URL adresa: | http://arxiv.org/abs/2409.13648 https://lirias.kuleuven.be/handle/20.500.12942/759455 https://doi.org/10.1145/3687935 |
| Rights: | CC BY arXiv Non-Exclusive Distribution |
| Prístupové číslo: | edsair.doi.dedup.....c22365979b7e34a61a68723add1c2d56 |
| Databáza: | OpenAIRE |
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstrakt: | Experiencing high-fidelity volumetric video as seamlessly as 2D videos is a long-held dream. However, current dynamic 3DGS methods, despite their high rendering quality, face challenges in streaming on mobile devices due to computational and bandwidth constraints. In this paper, we introduce V 3 (Viewing Volumetric Videos), a novel approach that enables high-quality mobile rendering through the streaming of dynamic Gaussians. Our key innovation is to view dynamic 3DGS as 2D videos, facilitating the use of hardware video codecs. Additionally, we propose a two-stage training strategy to reduce storage requirements with rapid training speed. The first stage employs hash encoding and shallow MLP to learn motion, then reduces the number of Gaussians through pruning to meet the streaming requirements, while the second stage fine tunes other Gaussian attributes using residual entropy loss and temporal loss to improve temporal continuity. This strategy, which disentangles motion and appearance, maintains high rendering quality with compact storage requirements. Meanwhile, we designed a multi-platform player to decode and render 2D Gaussian videos. Extensive experiments demonstrate the effectiveness of V 3 , outperforming other methods by enabling high-quality rendering and streaming on common devices, which is unseen before. As the first to stream dynamic Gaussians on mobile devices, our companion player offers users an unprecedented volumetric video experience, including smooth scrolling and instant sharing. Our project page with source code is available at https://authoritywang.github.io/v3/. |
|---|---|
| ISSN: | 15577368 07300301 |
| DOI: | 10.1145/3687935 |