This paper presents a robust approach to 3D Gaussian Splatting (3DGS) for practical applications involving real-world data challenges. The main contributions include modeling motion blur as a Gaussian distribution over camera poses, allowing for both camera pose refinement and motion blur correction. Additionally, the paper proposes mechanisms for defocus blur compensation and addressing color inconsistencies caused by ambient light, shadows, or camera-related factors. The proposed solutions integrate seamlessly with the 3DGS formulation while maintaining its benefits in terms of training efficiency and rendering speed. The authors experimentally validate their contributions on benchmark datasets including Scannet++ and Deblur-NeRF, achieving state-of-the-art results and consistent improvements over relevant baselines. The paper also addresses challenges such as pose errors, motion blur, defocus blur, and color inconsistencies, providing a comprehensive solution for robust 3DGS in real-world scenarios.This paper presents a robust approach to 3D Gaussian Splatting (3DGS) for practical applications involving real-world data challenges. The main contributions include modeling motion blur as a Gaussian distribution over camera poses, allowing for both camera pose refinement and motion blur correction. Additionally, the paper proposes mechanisms for defocus blur compensation and addressing color inconsistencies caused by ambient light, shadows, or camera-related factors. The proposed solutions integrate seamlessly with the 3DGS formulation while maintaining its benefits in terms of training efficiency and rendering speed. The authors experimentally validate their contributions on benchmark datasets including Scannet++ and Deblur-NeRF, achieving state-of-the-art results and consistent improvements over relevant baselines. The paper also addresses challenges such as pose errors, motion blur, defocus blur, and color inconsistencies, providing a comprehensive solution for robust 3DGS in real-world scenarios.