Representing Long Volumetric Video with Temporal Gaussian Hierarchy
ACM Transactions on Graphics · 19.12.2024 · 43 (6) · 1-18
DOI: 10.1145/3687919 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 19.11.2024. Verfasst von Zhen Xu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 43-mal zitiert (Crossref) und nennt 77 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
This paper aims to address the challenge of reconstructing long volumetric videos from multi-view RGB videos. Recent dynamic view synthesis methods leverage powerful 4D representations, like feature grids or point cloud sequences, to achieve high-quality rendering results. However, they are typically limited to short (1~2s) video clips and often suffer from large memory footprints when dealing with longer videos. To solve this issue, we propose a novel 4D representation, named Temporal Gaussian Hierarchy, to compactly model long volumetric videos. Our key observation is that there are generally various degrees of temporal redundancy in dynamic scenes, which consist of areas changing at different speeds. Motivated by this, our approach builds a multi-level hierarchy of 4D Gaussian primitives, where each level separately describes scene regions with different degrees of content change, and adaptively shares Gaussian primitives to represent unchanged scene content over different temporal segments, thus effectively reducing the number of Gaussian primitives. In addition, the tree-like structure of the Gaussian hierarchy allows us to efficiently represent the scene at a particular moment with a subset of Gaussian primitives, leading to nearly constant GPU memory usage during the training or rendering regardless of the video length. Moreover, we design a Compact Appearance Model that mixes diffuse and view-dependent Gaussians to further minimize the model size while maintaining the rendering quality. We also develop a rasterization pipeline of Gaussian primitives based on the hardware-accelerated technique to improve rendering speed. Extensive experimental results demonstrate the superiority of our method over alternative methods in terms of training cost, rendering speed, and storage usage. To our knowledge, this work is the first approach capable of efficiently handling hours of volumetric video data while maintaining state-of-the-art rendering quality.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Xu, Z., Xu, Y., Yu, Z., Peng, S., Sun, J., Bao, H., & Zhou, X. (2024). Representing Long Volumetric Video with Temporal Gaussian Hierarchy. ACM Transactions on Graphics, 43(6), 1-18. https://doi.org/10.1145/3687919
Vancouver
Xu Z, Xu Y, Yu Z, Peng S, Sun J, Bao H, et al. Representing Long Volumetric Video with Temporal Gaussian Hierarchy. ACM Transactions on Graphics. 2024;43(6):1-18. doi:10.1145/3687919
BibTeX
@article{Xu2024,
author = {Xu, Zhen and Xu, Yinghao and Yu, Zhiyuan and Peng, Sida and Sun, Jiaming and Bao, Hujun and Zhou, Xiaowei},
title = {Representing Long Volumetric Video with Temporal Gaussian Hierarchy},
journal = {ACM Transactions on Graphics},
year = {2024},
volume = {43},
number = {6},
pages = {1--18},
doi = {10.1145/3687919}
}
EUVIMED