GIFStream: 4D Gaussian-Based Immersive Video with Feature Stream
Abstract
Immersive video offers a 6-Dof-free viewing experience, potentially playing a key role in future video technology. Recently, 4D Gaussian Splatting has gained attention as an effective approach for immersive video due to its high rendering efficiency and quality, though maintaining quality with manageable storage remains challenging. To address this, we introduce GIFStream, a novel 4D Gaussian representation using a canonical space and a deformation field enhanced with time-dependent feature streams. These feature streams enable complex motion modeling and allow efficient compression by leveraging their motion-awareness and temporal correspondence. Additionally, we incorporate both temporal and spatial compression networks for end-to-end compression. Experimental results show that GIFStream delivers high-quality immersive video at 30 Mbps, with real-time rendering and fast decoding on an RTX 4090.
Cite
Text
Li et al. "GIFStream: 4D Gaussian-Based Immersive Video with Feature Stream." Conference on Computer Vision and Pattern Recognition, 2025. doi:10.1109/CVPR52734.2025.02027Markdown
[Li et al. "GIFStream: 4D Gaussian-Based Immersive Video with Feature Stream." Conference on Computer Vision and Pattern Recognition, 2025.](https://mlanthology.org/cvpr/2025/li2025cvpr-gifstream/) doi:10.1109/CVPR52734.2025.02027BibTeX
@inproceedings{li2025cvpr-gifstream,
title = {{GIFStream: 4D Gaussian-Based Immersive Video with Feature Stream}},
author = {Li, Hao and Li, Sicheng and Gao, Xiang and Batuer, Abudouaihati and Yu, Lu and Liao, Yiyi},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2025},
pages = {21761-21770},
doi = {10.1109/CVPR52734.2025.02027},
url = {https://mlanthology.org/cvpr/2025/li2025cvpr-gifstream/}
}