{"ID":2823384,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2601.00913","arxiv_id":"2601.00913","title":"Clean-GS: Semantic Mask-Guided Pruning for 3D Gaussian Splatting","abstract":"3D Gaussian Splatting produces high-quality scene reconstructions but generates hundreds of thousands of spurious Gaussians (floaters) scattered throughout the environment. These artifacts obscure objects of interest and inflate model sizes, hindering deployment in bandwidth-constrained applications. We present Clean-GS, a method for removing background clutter and floaters from 3DGS reconstructions using sparse semantic masks. Our approach combines whitelist-based spatial filtering with color-guided validation and outlier removal to achieve 60-80\\% model compression while preserving object quality. Unlike existing 3DGS pruning methods that rely on global importance metrics, Clean-GS uses semantic information from as few as 3 segmentation masks (1\\% of views) to identify and remove Gaussians not belonging to the target object. Our multi-stage approach consisting of (1) whitelist filtering via projection to masked regions, (2) depth-buffered color validation, and (3) neighbor-based outlier removal isolates monuments and objects from complex outdoor scenes. Experiments on Tanks and Temples show that Clean-GS reduces file sizes from 125MB to 47MB while maintaining rendering quality, making 3DGS models practical for web deployment and AR/VR applications. Our code is available at https://github.com/smlab-niser/clean-gs","short_abstract":"3D Gaussian Splatting produces high-quality scene reconstructions but generates hundreds of thousands of spurious Gaussians (floaters) scattered throughout the environment. These artifacts obscure objects of interest and inflate model sizes, hindering deployment in bandwidth-constrained applications. We present Clean-G...","url_abs":"https://arxiv.org/abs/2601.00913","url_pdf":"https://arxiv.org/pdf/2601.00913v1","authors":"[\"Subhankar Mishra\"]","published":"2026-01-01T05:02:45Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.LG\"]","methods":"[]","has_code":false,"code_links":[{"ID":605492,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2823384,"paper_url":"https://arxiv.org/abs/2601.00913","paper_title":"Clean-GS: Semantic Mask-Guided Pruning for 3D Gaussian Splatting","repo_url":"https://github.com/smlab-niser/clean-gs","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}