SurfaceSplat：连接表面重建与高斯泼溅
SurfaceSplat: Connecting Surface Reconstruction and Gaussian Splatting
AI总结：
本文提出SurfaceSplat混合框架，通过SDF与3DGS相互增强，在DTU和MobileBrick上提升稀疏视图表面重建与新视角合成性能。
摘要：
从稀疏视图图像进行表面重建和新视角渲染颇具挑战性。基于符号距离函数（SDF）的方法难以处理精细细节，而基于3D高斯泼溅（3DGS）的方法缺乏全局几何一致性。我们提出一种新颖的混合方法，结合两者优势：SDF捕捉粗略几何以增强基于3DGS的渲染，同时由3DGS新渲染的图像细化SDF的细节，从而实现准确的表面重建。因此，我们的方法在DTU和MobileBrick数据集上的表面重建和新视角合成方面超越了现有最先进方法。代码将发布于https://github.com/aim-uofa/SurfaceSplat。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
