{"ID":2892172,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.15454","arxiv_id":"2507.15454","title":"ObjectGS: Object-aware Scene Reconstruction and Scene Understanding via Gaussian Splatting","abstract":"3D Gaussian Splatting is renowned for its high-fidelity reconstructions and real-time novel view synthesis, yet its lack of semantic understanding limits object-level perception. In this work, we propose ObjectGS, an object-aware framework that unifies 3D scene reconstruction with semantic understanding. Instead of treating the scene as a unified whole, ObjectGS models individual objects as local anchors that generate neural Gaussians and share object IDs, enabling precise object-level reconstruction. During training, we dynamically grow or prune these anchors and optimize their features, while a one-hot ID encoding with a classification loss enforces clear semantic constraints. We show through extensive experiments that ObjectGS not only outperforms state-of-the-art methods on open-vocabulary and panoptic segmentation tasks, but also integrates seamlessly with applications like mesh extraction and scene editing. Project page: https://ruijiezhu94.github.io/ObjectGS_page","short_abstract":"3D Gaussian Splatting is renowned for its high-fidelity reconstructions and real-time novel view synthesis, yet its lack of semantic understanding limits object-level perception. In this work, we propose ObjectGS, an object-aware framework that unifies 3D scene reconstruction with semantic understanding. Instead of tre...","url_abs":"https://arxiv.org/abs/2507.15454","url_pdf":"https://arxiv.org/pdf/2507.15454v1","authors":"[\"Ruijie Zhu\",\"Mulin Yu\",\"Linning Xu\",\"Lihan Jiang\",\"Yixuan Li\",\"Tianzhu Zhang\",\"Jiangmiao Pang\",\"Bo Dai\"]","published":"2025-07-21T10:06:23Z","proceeding":"cs.GR","tasks":"[\"cs.GR\",\"cs.AI\",\"cs.CV\",\"cs.HC\"]","methods":"[]","has_code":false}