CVPR2025
DeSplat: Decomposed Gaussian Splatting for Distractor-Free Rendering
Yihao Wang, Marcus Klasson, Matias Turkulainen, Shuzhe Wang, Juho Kannala, Arno Solin
摘要
Moving objects in the views easily break multi-view consistency Distractor Gaussians Figure 1. DeSplat: Gaussian Splatting struggles with floaters and artifacts when image sequences violate photometric consistency assumptions. Unlike existing distractor-free methods which rely on external semantic features, we propose a fully splatting-based solution grounded in photometric consistency that decomposes 3DGS scenes into static components and per-view distractors.