{"ID":2892820,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.14596","arxiv_id":"2507.14596","title":"DiSCO-3D : Discovering and segmenting Sub-Concepts from Open-vocabulary queries in NeRF","abstract":"3D semantic segmentation provides high-level scene understanding for applications in robotics, autonomous systems, \\textit{etc}. Traditional methods adapt exclusively to either task-specific goals (open-vocabulary segmentation) or scene content (unsupervised semantic segmentation). We propose DiSCO-3D, the first method addressing the broader problem of 3D Open-Vocabulary Sub-concepts Discovery, which aims to provide a 3D semantic segmentation that adapts to both the scene and user queries. We build DiSCO-3D on Neural Fields representations, combining unsupervised segmentation with weak open-vocabulary guidance. Our evaluations demonstrate that DiSCO-3D achieves effective performance in Open-Vocabulary Sub-concepts Discovery and exhibits state-of-the-art results in the edge cases of both open-vocabulary and unsupervised segmentation.","short_abstract":"3D semantic segmentation provides high-level scene understanding for applications in robotics, autonomous systems, \\textit{etc}. Traditional methods adapt exclusively to either task-specific goals (open-vocabulary segmentation) or scene content (unsupervised semantic segmentation). We propose DiSCO-3D, the first method...","url_abs":"https://arxiv.org/abs/2507.14596","url_pdf":"https://arxiv.org/pdf/2507.14596v1","authors":"[\"Doriand Petit\",\"Steve Bourgeois\",\"Vincent Gay-Bellile\",\"Florian Chabot\",\"Loïc Barthe\"]","published":"2025-07-19T12:46:20Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}