{"ID":2837972,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.18386","arxiv_id":"2511.18386","title":"SegSplat: Feed-forward Gaussian Splatting and Open-Set Semantic Segmentation","abstract":"We have introduced SegSplat, a novel framework designed to bridge the gap between rapid, feed-forward 3D reconstruction and rich, open-vocabulary semantic understanding. By constructing a compact semantic memory bank from multi-view 2D foundation model features and predicting discrete semantic indices alongside geometric and appearance attributes for each 3D Gaussian in a single pass, SegSplat efficiently imbues scenes with queryable semantics. Our experiments demonstrate that SegSplat achieves geometric fidelity comparable to state-of-the-art feed-forward 3D Gaussian Splatting methods while simultaneously enabling robust open-set semantic segmentation, crucially \\textit{without} requiring any per-scene optimization for semantic feature integration. This work represents a significant step towards practical, on-the-fly generation of semantically aware 3D environments, vital for advancing robotic interaction, augmented reality, and other intelligent systems.","short_abstract":"We have introduced SegSplat, a novel framework designed to bridge the gap between rapid, feed-forward 3D reconstruction and rich, open-vocabulary semantic understanding. By constructing a compact semantic memory bank from multi-view 2D foundation model features and predicting discrete semantic indices alongside geometr...","url_abs":"https://arxiv.org/abs/2511.18386","url_pdf":"https://arxiv.org/pdf/2511.18386v1","authors":"[\"Peter Siegel\",\"Federico Tombari\",\"Marc Pollefeys\",\"Daniel Barath\"]","published":"2025-11-23T10:26:38Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}