Optimizing 3D Gaussian Splatting for Sparse Viewpoint Scene Reconstruction
This addresses limitations in 3D scene reconstruction for robotics and computer vision applications, representing an incremental improvement over existing 3D Gaussian Splatting methods.
The paper tackles the problem of 3D Gaussian Splatting's susceptibility to artifacts and poor performance with sparse viewpoints, introducing SVS-GS which integrates smoothing filters, depth priors, and diffusion to improve reconstruction. Experimental results on MipNeRF-360 and SeaThru-NeRF datasets show marked improvements in 3D reconstruction from sparse viewpoints.
3D Gaussian Splatting (3DGS) has emerged as a promising approach for 3D scene representation, offering a reduction in computational overhead compared to Neural Radiance Fields (NeRF). However, 3DGS is susceptible to high-frequency artifacts and demonstrates suboptimal performance under sparse viewpoint conditions, thereby limiting its applicability in robotics and computer vision. To address these limitations, we introduce SVS-GS, a novel framework for Sparse Viewpoint Scene reconstruction that integrates a 3D Gaussian smoothing filter to suppress artifacts. Furthermore, our approach incorporates a Depth Gradient Profile Prior (DGPP) loss with a dynamic depth mask to sharpen edges and 2D diffusion with Score Distillation Sampling (SDS) loss to enhance geometric consistency in novel view synthesis. Experimental evaluations on the MipNeRF-360 and SeaThru-NeRF datasets demonstrate that SVS-GS markedly improves 3D reconstruction from sparse viewpoints, offering a robust and efficient solution for scene understanding in robotics and computer vision applications.