EvoGS: Modeling Deformation Evolution for Dynamic Gaussian Splatting

arXiv:2609.00994v1 Announce Type: new 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 extbf{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.

Related

• D^2-4DGS: Dual-Depth Guided Sparse-Camera 4D Gaussian Splatting
• 4D Neural Voxel Splatting: Dynamic Scene Rendering with Voxelized Guassian Splatting
• Learning Stable Canonical Worlds for Novel View Synthesis and Beyond

Source: arXiv cs.CV | 2026-09-02