DeSplat: Decomposed Gaussian Splatting for Distractor-Free Rendering
This addresses the challenge of accurate 3D reconstruction in real-world scenes with distractors for applications in computer vision and graphics, representing an incremental improvement by eliminating the need for pre-trained models.
The paper tackles the problem of distractor-free novel view synthesis in 3D environments by proposing DeSplat, a method that separates distractors from static scenes using Gaussian splatting without external semantic information, achieving comparable results to prior approaches while maintaining rendering speed.
Gaussian splatting enables fast novel view synthesis in static 3D environments. However, reconstructing real-world environments remains challenging as distractors or occluders break the multi-view consistency assumption required for accurate 3D reconstruction. Most existing methods rely on external semantic information from pre-trained models, introducing additional computational overhead as pre-processing steps or during optimization. In this work, we propose a novel method, DeSplat, that directly separates distractors and static scene elements purely based on volume rendering of Gaussian primitives. We initialize Gaussians within each camera view for reconstructing the view-specific distractors to separately model the static 3D scene and distractors in the alpha compositing stages. DeSplat yields an explicit scene separation of static elements and distractors, achieving comparable results to prior distractor-free approaches without sacrificing rendering speed. We demonstrate DeSplat's effectiveness on three benchmark data sets for distractor-free novel view synthesis. See the project website at https://aaltoml.github.io/desplat/.