Motivation of VDEGaussian.
Overview of VDEGaussian.
Qualitative Results on Waymo.
Dynamic urban scene modeling is a rapidly evolving area with broad applications. While current approaches leveraging neural radiance fields or Gaussian Splatting have achieved fine-grained reconstruction and high-fidelity novel view synthesis, they still face significant limitations. These often stem from a dependence on pre-calibrated object tracks or difficulties in accurately modeling fast-moving objects from undersampled capture, particularly due to challenges in handling temporal discontinuities. To overcome these issues, we propose a novel video diffusion-enhanced 4D Gaussian Splatting framework. Our key insight is to distill robust, temporally consistent priors from a test-time adapted video diffusion model. To ensure precise pose alignment and effective integration of this denoised content, we introduce two core innovations: a joint timestamp optimization strategy that refines interpolated frame poses, and an uncertainty distillation method that adaptively extracts target content while preserving well-reconstructed regions. Extensive experiments demonstrate that our method significantly enhances dynamic modeling, especially for fast-moving objects, achieving an approximate PSNR gain of 2 dB for novel view synthesis over baseline approaches.
@misc{xiao2025vdegaussianvideodiffusionenhanced,
title={VDEGaussian: Video Diffusion Enhanced 4D Gaussian Splatting for Dynamic Urban Scenes Modeling},
author={Yuru Xiao and Zihan Lin and Chao Lu and Deming Zhai and Kui Jiang and Wenbo Zhao and Wei Zhang and Junjun Jiang and Huanran Wang and Xianming Liu},
year={2025},
eprint={2508.02129},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2508.02129},
}