{"ID":2885715,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.04297","arxiv_id":"2508.04297","title":"MuGS: Multi-Baseline Generalizable Gaussian Splatting Reconstruction","abstract":"We present Multi-Baseline Gaussian Splatting (MuGS), a generalized feed-forward approach for novel view synthesis that effectively handles diverse baseline settings, including sparse input views with both small and large baselines. Specifically, we integrate features from Multi-View Stereo (MVS) and Monocular Depth Estimation (MDE) to enhance feature representations for generalizable reconstruction. Next, We propose a projection-and-sampling mechanism for deep depth fusion, which constructs a fine probability volume to guide the regression of the feature map. Furthermore, We introduce a reference-view loss to improve geometry and optimization efficiency. We leverage 3D Gaussian representations to accelerate training and inference time while enhancing rendering quality. MuGS achieves state-of-the-art performance across multiple baseline settings and diverse scenarios ranging from simple objects (DTU) to complex indoor and outdoor scenes (RealEstate10K). We also demonstrate promising zero-shot performance on the LLFF and Mip-NeRF 360 datasets. Code is available at https://github.com/EuclidLou/MuGS.","short_abstract":"We present Multi-Baseline Gaussian Splatting (MuGS), a generalized feed-forward approach for novel view synthesis that effectively handles diverse baseline settings, including sparse input views with both small and large baselines. Specifically, we integrate features from Multi-View Stereo (MVS) and Monocular Depth Est...","url_abs":"https://arxiv.org/abs/2508.04297","url_pdf":"https://arxiv.org/pdf/2508.04297v2","authors":"[\"Yaopeng Lou\",\"Liao Shen\",\"Tianqi Liu\",\"Jiaqi Li\",\"Zihao Huang\",\"Huiqiang Sun\",\"Zhiguo Cao\"]","published":"2025-08-06T10:34:24Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":611230,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2885715,"paper_url":"https://arxiv.org/abs/2508.04297","paper_title":"MuGS: Multi-Baseline Generalizable Gaussian Splatting Reconstruction","repo_url":"https://github.com/EuclidLou/MuGS","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}