* The Lecturer dataset will be released soon. Dancer dataset will not be released due to copyright issues.
We have recently seen great progress in 3D scene reconstruction through explicit point-based 3D Gaussian Splatting (3DGS), notable for its high quality and fast rendering speed. However, reconstructing dynamic scenes such as complex human performances with long durations remains challenging. Prior efforts fall short of modeling a long-term sequence with drastic motions, frequent topology changes or interactions with props, and resort to segmenting the whole sequence into groups of frames that are processed independently, which undermines temporal stability and thereby leads to an unpleasant viewing experience and inefficient storage footprint. In view of this, we introduce EvolvingGS, a two-stage strategy that first deforms the Gaussian model to coarsely align with the target frame, and then refines it with minimal point addition/subtraction, particularly in fast-changing areas. Owing to the flexibility of the incrementally evolving representation, our method outperforms existing approaches in terms of both per-frame and temporal quality metrics while maintaining fast rendering through its purely explicit representation. Moreover, by exploiting temporal coherence between successive frames, we propose a simple yet effective compression algorithm that achieves over 50x compression rate. Extensive experiments on both public benchmarks and challenging custom datasets demonstrate that our method significantly advances the state-of-the-art in dynamic scene reconstruction, particularly for extended sequences with complex human performances.
Our EvolvingGS framework enables continuous reconstruction of dynamic sequences (top) across diverse scenarios (bottom). Our approach maintains temporal continuity throughout long performance sequences with complex motions and clothing deformation without relying on global keyframe switching. The method achieves efficient compression across varied capture scenarios, with over 50x compression rate while preserving visual quality.
@misc{zhang2025evolvinggshighfidelitystreamablevolumetric,
title={EvolvingGS: High-Fidelity Streamable Volumetric Video via Evolving 3D Gaussian Representation},
author={Chao Zhang and Yifeng Zhou and Shuheng Wang and Wenfa Li and Degang Wang and Yi Xu and Shaohui Jiao},
year={2025},
eprint={2503.05162},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2503.05162},
}