4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos

NeurIPSSpotlight2025

Authors
Zhen Xu, Zhengqin Li, Zhao Dong, Xiaowei Zhou, Richard Newcombe, Zhaoyang Lv
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

We propose 4DGT, a 4D Gaussian-based Transformer model for dynamic scene reconstruction, trained entirely on real-world monocular posed videos…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

transformer video

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive