GA-GS: Generation-Assisted Gaussian Splatting for Static Scene Reconstruction

TL;DR

GA-GS introduces a novel method for static scene reconstruction from monocular videos with dynamic objects by leveraging generation and inpainting techniques to recover occluded regions, achieving state-of-the-art results.

Contribution

The paper proposes a generation-assisted Gaussian splatting approach that uses diffusion models and a learnable authenticity scalar to improve occluded region reconstruction in static scenes.

Findings

Achieves state-of-the-art performance on reconstruction benchmarks.

Effectively inpaints occluded regions using diffusion models.

Demonstrates robustness in scenarios with large occlusions.

Abstract

Reconstructing static 3D scene from monocular video with dynamic objects is important for numerous applications such as virtual reality and autonomous driving. Current approaches typically rely on background for static scene reconstruction, limiting the ability to recover regions occluded by dynamic objects. In this paper, we propose GA-GS, a Generation-Assisted Gaussian Splatting method for Static Scene Reconstruction. The key innovation of our work lies in leveraging generation to assist in reconstructing occluded regions. We employ a motion-aware module to segment and remove dynamic regions, and thenuse a diffusion model to inpaint the occluded areas, providing pseudo-ground-truth supervision. To balance contributions from real background and generated region, we introduce a learnable authenticity scalar for each Gaussian primitive, which dynamically modulates opacity during splatting for authenticity-aware rendering and supervision. Since no existing dataset provides ground-truth static scene of video with dynamic objects, we construct a dataset named Trajectory-Match, using a fixed-path robot to record each scene with/without dynamic objects, enabling quantitative evaluation in reconstruction of occluded regions. Extensive experiments on both the DAVIS and our dataset show that GA-GS achieves state-of-the-art performance in static scene reconstruction, especially in challenging scenarios with large-scale, persistent occlusions.