Split4D: Decomposed 4D Scene Reconstruction Without Video Segmentation
ACM Transactions on Graphics · 2025-12 · 44 (6) · 1-15
DOI: 10.1145/3763343 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 04.12.2025. Verfasst von Yongzhen Hu und 10 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 67 Literaturangaben. Gefördert von: National Key Research and Development Program of China.
Abstract (Originalsprache)
This paper addresses the problem of decomposed 4D scene reconstruction from multi-view videos. Recent methods achieve this by lifting video segmentation results to a 4D representation through differentiable rendering techniques. Therefore, they heavily rely on the quality of video segmentation maps, which are often unstable, leading to unreliable reconstruction results. To overcome this challenge, our key idea is to represent the decomposed 4D scene with the Freetime FeatureGS and design a streaming feature learning strategy to accurately recover it from per-image segmentation maps, eliminating the need for video segmentation. Freetime FeatureGS models the dynamic scene as a set of Gaussian primitives with learnable features and linear motion ability, allowing them to move to neighboring regions over time. We apply a contrastive loss to Freetime FeatureGS, forcing primitive features to be close or far apart based on whether their projections belong to the same instance in the 2D segmentation map. As our Gaussian primitives can move across time, it naturally extends the feature learning to the temporal dimension, achieving 4D segmentation. Furthermore, we sample observations for training in a temporally ordered manner, enabling the streaming propagation of features over time and effectively avoiding local minima during the optimization process. Experimental results on several datasets show that the reconstruction quality of our method outperforms recent methods by a large margin.
Förderung
- National Key Research and Development Program of China
Zitieren
APA
Hu, Y., Yang, Y., Lin, H., Wang, Y., Dong, J., Deng, Y., Zhu, X., Jia, F., Bao, H., Zhou, X., & Peng, S. (2025). Split4D: Decomposed 4D Scene Reconstruction Without Video Segmentation. ACM Transactions on Graphics, 44(6), 1-15. https://doi.org/10.1145/3763343
Vancouver
Hu Y, Yang Y, Lin H, Wang Y, Dong J, Deng Y, et al. Split4D: Decomposed 4D Scene Reconstruction Without Video Segmentation. ACM Transactions on Graphics. 2025;44(6):1-15. doi:10.1145/3763343
BibTeX
@article{Hu2025,
author = {Hu, Yongzhen and Yang, Yihui and Lin, Haotong and Wang, Yifan and Dong, Junting and Deng, Yifu and Zhu, Xinyu and Jia, Fan and Bao, Hujun and Zhou, Xiaowei and Peng, Sida},
title = {Split4D: Decomposed 4D Scene Reconstruction Without Video Segmentation},
journal = {ACM Transactions on Graphics},
year = {2025},
volume = {44},
number = {6},
pages = {1--15},
doi = {10.1145/3763343}
}
EUVIMED