{"ID":2857941,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.07839","arxiv_id":"2510.07839","title":"AlignGS: Aligning Geometry and Semantics for Robust Indoor Reconstruction from Sparse Views","abstract":"The demand for semantically rich 3D models of indoor scenes is rapidly growing, driven by applications in augmented reality, virtual reality, and robotics. However, creating them from sparse views remains a challenge due to geometric ambiguity. Existing methods often treat semantics as a passive feature painted on an already-formed, and potentially flawed, geometry. We posit that for robust sparse-view reconstruction, semantic understanding instead be an active, guiding force. This paper introduces AlignGS, a novel framework that actualizes this vision by pioneering a synergistic, end-to-end optimization of geometry and semantics. Our method distills rich priors from 2D foundation models and uses them to directly regularize the 3D representation through a set of novel semantic-to-geometry guidance mechanisms, including depth consistency and multi-faceted normal regularization. Extensive evaluations on standard benchmarks demonstrate that our approach achieves state-of-the-art results in novel view synthesis and produces reconstructions with superior geometric accuracy. The results validate that leveraging semantic priors as a geometric regularizer leads to more coherent and complete 3D models from limited input views. Our code is avaliable at https://github.com/MediaX-SJTU/AlignGS .","short_abstract":"The demand for semantically rich 3D models of indoor scenes is rapidly growing, driven by applications in augmented reality, virtual reality, and robotics. However, creating them from sparse views remains a challenge due to geometric ambiguity. Existing methods often treat semantics as a passive feature painted on an a...","url_abs":"https://arxiv.org/abs/2510.07839","url_pdf":"https://arxiv.org/pdf/2510.07839v1","authors":"[\"Yijie Gao\",\"Houqiang Zhong\",\"Tianchi Zhu\",\"Zhengxue Cheng\",\"Qiang Hu\",\"Li Song\"]","published":"2025-10-09T06:30:20Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":608502,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2857941,"paper_url":"https://arxiv.org/abs/2510.07839","paper_title":"AlignGS: Aligning Geometry and Semantics for Robust Indoor Reconstruction from Sparse Views","repo_url":"https://github.com/MediaX-SJTU/AlignGS","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}