{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:35:23Z","timestamp":1773801323789,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.1609\/aaai.v40i5.37393","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T23:05:38Z","timestamp":1773788738000},"page":"3912-3920","source":"Crossref","is-referenced-by-count":0,"title":["Sparse3DPR: Training-Free 3D Hierarchical Scene Parsing and Task-Adaptive Subgraph Reasoning from Sparse RGB Views"],"prefix":"10.1609","volume":"40","author":[{"given":"Haida","family":"Feng","sequence":"first","affiliation":[]},{"given":"Hao","family":"Wei","sequence":"additional","affiliation":[]},{"given":"Zewen","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Haolin","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Chade","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yihong","family":"Wu","sequence":"additional","affiliation":[]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/37393\/41355","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/37393\/41355","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T23:05:39Z","timestamp":1773788739000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/37393"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i5.37393","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}