arXiv cs.AI· Yijie Su, Yakun Zhu, Yi Bin, Pengpeng Zeng, Liang Chen, Guoqing Wang, Jingkuan Song, Heng Tao Shen·· 2 天前AI 评分18
BridgeAfford：弥合查询-目标差距的通用 3D 可供性定位框架
BridgeAfford: Bridging Query-Target Gap for Generalizable 3D Affordance Grounding
AI 导读
BridgeAfford 通过交互区域对齐（IRA）和视觉证据聚合（VEA）两个机制弥合查询与目标区域间的语义差距，提升 3D 可供性定位对未见物体的泛化能力。在 LASO 和 PIAD 数据集上，该方法优于现有方案，尤其在未见物体上表现突出。
正文 · 原文
Abstract:Language-guided 3D affordance grounding aims to localize functional regions on 3D objects according to interaction intents. However, existing methods exhibit poor generalization to unseen objects. One challenge is the query-target gap: a semantic discrepancy between query features encoding interaction intents and target-region features, leading to inaccurate grounding. End-to-end training favors query representations tailored to seen objects, limiting their compatibility with shifted target-region features on unseen objects. To address this issue, we propose BridgeAfford, a framework that reduces the query-target semantic gap from two complementary perspectives. First, Interaction Region Alignment (IRA) promotes cross-object alignment among geometrically similar interaction regions during training. This enables structures on unseen objects that resemble previously observed ones to produce representations similar to those learned during training, facilitating target-region recognition. Second, Visual Evidence Aggregation (VEA) leverages a 2D affordance model to refine the attention distribution and guide the query toward the correct region, yielding more target-aware queries. Extensive experiments on the LASO and PIAD datasets demonstrate that BridgeAfford outperforms existing methods, particularly on unseen objects, highlighting its robust generalization ability.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.21918 [cs.CV] |
| (or arXiv:2610.21918v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.21918 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yijie Su [view email]
[v1]
Thu, 15 Oct 2026 14:03:16 UTC (4,506 KB)
来源：arXiv cs.AI · arxiv.org