{"ID":2892259,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.15602","arxiv_id":"2507.15602","title":"SurfaceSplat: Connecting Surface Reconstruction and Gaussian Splatting","abstract":"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.","short_abstract":"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 appro...","url_abs":"https://arxiv.org/abs/2507.15602","url_pdf":"https://arxiv.org/pdf/2507.15602v2","authors":"[\"Zihui Gao\",\"Jia-Wang Bian\",\"Guosheng Lin\",\"Hao Chen\",\"Chunhua Shen\"]","published":"2025-07-21T13:25:03Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":611977,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2892259,"paper_url":"https://arxiv.org/abs/2507.15602","paper_title":"SurfaceSplat: Connecting Surface Reconstruction and Gaussian Splatting","repo_url":"https://github.com/aim-uofa/SurfaceSplat","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}