DeGauss: Dynamic-Static Decomposition with Gaussian Splatting for Distractor-free 3D Reconstruction
This addresses the challenge of 3D reconstruction in highly dynamic, interaction-rich environments for applications like robotics or AR/VR, though it appears incremental as it builds on Gaussian Splatting with a novel decomposition approach.
The paper tackles the problem of reconstructing clean, distractor-free 3D scenes from real-world captures in dynamic and cluttered settings, such as egocentric videos, by introducing DeGauss, a self-supervised framework that uses a decoupled dynamic-static Gaussian Splatting design, and it consistently outperforms existing methods on benchmarks like NeRF-on-the-go, ADT, AEA, Hot3D, and EPIC-Fields.
Reconstructing clean, distractor-free 3D scenes from real-world captures remains a significant challenge, particularly in highly dynamic and cluttered settings such as egocentric videos. To tackle this problem, we introduce DeGauss, a simple and robust self-supervised framework for dynamic scene reconstruction based on a decoupled dynamic-static Gaussian Splatting design. DeGauss models dynamic elements with foreground Gaussians and static content with background Gaussians, using a probabilistic mask to coordinate their composition and enable independent yet complementary optimization. DeGauss generalizes robustly across a wide range of real-world scenarios, from casual image collections to long, dynamic egocentric videos, without relying on complex heuristics or extensive supervision. Experiments on benchmarks including NeRF-on-the-go, ADT, AEA, Hot3D, and EPIC-Fields demonstrate that DeGauss consistently outperforms existing methods, establishing a strong baseline for generalizable, distractor-free 3D reconstructionin highly dynamic, interaction-rich environments. Project page: https://batfacewayne.github.io/DeGauss.io/