融合SDF与高斯喷溅，实现更精确的表面重建与新视角合成。
SurfaceSplat: Connecting Surface Reconstruction and Gaussian Splatting
- 用SDF捕捉粗略几何，指导3DGS渲染
- 3DGS生成图像反向优化SDF细节
- 在DTU和MobileBrick上性能领先
从稀疏视角图像进行表面重建和新视角渲染仍具挑战。基于符号距离函数（SDF）的方法难以保留精细结构，而基于3D高斯喷溅（3DGS）的方法缺乏全局几何一致性。本文提出一种新型混合方法：SDF捕获粗略几何以提升3DGS渲染质量，同时3DGS生成的新图像反过来细化SDF细节，实现更准确的表面重建。实验表明，该方法在DTU和MobileBrick数据集上的表面重建与新视角合成性能均优于当前最优方法。代码将发布于https://github.com/aim-uofa/SurfaceSplat。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。