EvoGS: Modeling Deformation Evolution for Dynamic Gaussian Splatting

2026-09-01

AI Summary

EvoGS通过建模高斯变形的时间演化过程，解决了动态场景中3D高斯点云渲染对大或突变动不鲁棒的问题。

Abstract

Recent extensions of 3D Gaussian Splatting (3DGS) enable real-time novel view synthesis in dynamic scenes by learning time-conditioned Gaussian deformations. However, existing MLP-based methods typically estimate deformations independently at each timestamp, making them less robust to large or abrupt motions. To address this issue, we propose \textbf{EvoGS}, a 3DGS-based dynamic reconstruction framework that models Gaussian deformation as a temporal evolution process. EvoGS maintains persistent deformation states for each Gaussian, extrapolates future states from historical deformation states, and corrects the predictions with MLP-derived observations. The correction is adaptively weighted using a temporal residual memory and evolution statistics such as deformation velocity and trajectory deviation. To further improve reconstruction quality, EvoGS introduces deformation-aware densification. Clone and split operations are performed along corrected deformation directions, while an uncertainty-aware strategy suppresses densification for Gaussians with unstable deformation histories. Experiments show that EvoGS improves dynamic novel view synthesis quality and achieves competitive performance across benchmarks.

Problem

• Dynamic Scenes
• Gaussian Deformation
• Temporal Evolution
• Deformation Robustness
• Real-time Novel View Synthesis

Innovation

• Temporal Evolution
• Deformation Modeling
• Adaptive Correction
• Deformation-aware Densification