SurfaceSplat: Connecting Surface Reconstruction and Gaussian Splatting
This addresses the problem of achieving accurate and detailed 3D reconstructions for applications in computer vision and graphics, representing an incremental improvement by integrating existing methods.
The paper tackles the challenge of surface reconstruction and novel view rendering from sparse-view images by proposing a hybrid method that combines SDF for coarse geometry and 3DGS for detail refinement, resulting in state-of-the-art performance on DTU and MobileBrick datasets.
Surface reconstruction and novel view rendering from sparse-view images are challenging. Signed Distance Function (SDF)-based methods struggle with fine details, while 3D Gaussian Splatting (3DGS)-based approaches lack global geometry coherence. We propose a novel hybrid method that combines the strengths of both approaches: SDF captures coarse geometry to enhance 3DGS-based rendering, while newly rendered images from 3DGS refine the details of SDF for accurate surface reconstruction. As a result, our method surpasses state-of-the-art approaches in surface reconstruction and novel view synthesis on the DTU and MobileBrick datasets. Code will be released at https://github.com/aim-uofa/SurfaceSplat.