{"ID":2843127,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.07813","arxiv_id":"2511.07813","title":"Sparse3DPR: Training-Free 3D Hierarchical Scene Parsing and Task-Adaptive Subgraph Reasoning from Sparse RGB Views","abstract":"Recently, large language models (LLMs) have been explored widely for 3D scene understanding. Among them, training-free approaches are gaining attention for their flexibility and generalization over training-based methods. However, they typically struggle with accuracy and efficiency in practical deployment. To address the problems, we propose Sparse3DPR, a novel training-free framework for open-ended scene understanding, which leverages the reasoning capabilities of pre-trained LLMs and requires only sparse-view RGB inputs. Specifically, we introduce a hierarchical plane-enhanced scene graph that supports open vocabulary and adopts dominant planar structures as spatial anchors, which enables clearer reasoning chains and more reliable high-level inferences. Furthermore, we design a task-adaptive subgraph extraction method to filter query-irrelevant information dynamically, reducing contextual noise and improving 3D scene reasoning efficiency and accuracy. Experimental results demonstrate the superiority of Sparse3DPR, which achieves a 28.7% EM@1 improvement and a 78.2% speedup compared with ConceptGraphs on the Space3D-Bench. Moreover, Sparse3DPR obtains comparable performance to training-based methods on ScanQA, with additional real-world experiments confirming its robustness and generalization capability.","short_abstract":"Recently, large language models (LLMs) have been explored widely for 3D scene understanding. Among them, training-free approaches are gaining attention for their flexibility and generalization over training-based methods. However, they typically struggle with accuracy and efficiency in practical deployment. To address...","url_abs":"https://arxiv.org/abs/2511.07813","url_pdf":"https://arxiv.org/pdf/2511.07813v1","authors":"[\"Haida Feng\",\"Hao Wei\",\"Zewen Xu\",\"Haolin Wang\",\"Chade Li\",\"Yihong Wu\"]","published":"2025-11-11T04:13:54Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}