EvoGS: Modeling Deformation Evolution for Dynamic Gaussian Splatting

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 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.

Authors

Institutions

Publication Details

Journal
Computer Graphics Forum
Published
2026-11-14
DOI
https://doi.org/10.1111/cgf.70602
Primary Topic
3D Shape Modeling and Analysis
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

EvoGS: Modeling Deformation Evolution for Dynamic Gaussian Splatting

Shahram Shirani, Jun Chen, Wei Dong, Han Zhou
1 links
Computer Graphics Forum
3D Shape Modeling and Analysis
article

EvoGS: Modeling Deformation Evolution for Dynamic Gaussian Splatting

Shahram Shirani, Jun Chen, Wei Dong, Han Zhou
article en

Abstract

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 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.

Computer Graphics Forum
McMaster University (CA)
3D Shape Modeling and Analysis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon