Robust Gaussian Splatting
This addresses practical robustness issues in 3D reconstruction for real-world applications, representing an incremental improvement to the 3DGS method.
The paper tackles error sources in 3D Gaussian Splatting (3DGS) such as blur, imperfect camera poses, and color inconsistencies to improve robustness for applications like handheld phone captures, achieving state-of-the-art results on benchmarks like Scannet++ and Deblur-NeRF.
In this paper, we address common error sources for 3D Gaussian Splatting (3DGS) including blur, imperfect camera poses, and color inconsistencies, with the goal of improving its robustness for practical applications like reconstructions from handheld phone captures. Our main contribution involves modeling motion blur as a Gaussian distribution over camera poses, allowing us to address both camera pose refinement and motion blur correction in a unified way. Additionally, we propose mechanisms for defocus blur compensation and for addressing color in-consistencies caused by ambient light, shadows, or due to camera-related factors like varying white balancing settings. Our proposed solutions integrate in a seamless way with the 3DGS formulation while maintaining its benefits in terms of training efficiency and rendering speed. We experimentally validate our contributions on relevant benchmark datasets including Scannet++ and Deblur-NeRF, obtaining state-of-the-art results and thus consistent improvements over relevant baselines.