{"ID":5551686,"CreatedAt":"2026-07-02T01:54:51.863792489Z","UpdatedAt":"2026-07-04T12:48:09.865479953Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.00889","arxiv_id":"2607.00889","title":"DeWorldSG: Depth-Aware 3D Semantic Scene Graph Generation via World-Model Priors","abstract":"We present DeWorldSG, a novel framework that generates spatio-temporally robust 3D Semantic Scene Graphs from RGB-D sequences. Existing methods often struggle to construct reliable 3D scene graphs due to unstable 3D object representations and missing relations caused by frame-wise inference. DeWorldSG addresses these issues by estimating instance-level geometric 3D Gaussian distributions through depth-guided filtering and representing each object as a probabilistic 3D node rather than a single projected point. To mitigate relational sparsity from frame-wise inference, our framework further aggregates spatiotemporal evidence across object pairs and refines relations using contextual priors derived from a world model (V-JEPA 2). Experiments on the 3DSSG and ReplicaSSG datasets demonstrate state-of-the-art (SoTA) performance in both object and predicate prediction, while producing temporally consistent scene structures. In particular, our method improves triplet recall by 77.4% and predicate recall by 23.2% over prior SoTA approaches, making it suitable for robotic manipulation and AR applications. Our code and models are open-sourced.","short_abstract":"We present DeWorldSG, a novel framework that generates spatio-temporally robust 3D Semantic Scene Graphs from RGB-D sequences. Existing methods often struggle to construct reliable 3D scene graphs due to unstable 3D object representations and missing relations caused by frame-wise inference. DeWorldSG addresses these i...","url_abs":"https://arxiv.org/abs/2607.00889","url_pdf":"https://arxiv.org/pdf/2607.00889v1","authors":"[\"Seok-Young Kim\",\"Abdelrahman Elskhawy\",\"Taewook Ha\",\"Dooyoung Kim\",\"Eunjae Shin\",\"Benjamin Busam\",\"Woontack Woo\"]","published":"2026-07-01T12:55:09Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[]","has_code":false}