# BridgeAfford：弥合查询-目标差距以实现可泛化的3D Affordance Grounding

> 原文链接：https://robotics.hellobike.com/papers/2026-10-15-2610-21918
> 频道：papers | 更新日期：2026-10-15 | 标签：arxiv, cs.RO
> 核心摘要：针对未见物体3D功能区域定位泛化差的问题，BridgeAfford通过区域对齐与视觉证据聚合，在LASO和PIAD上验证有效。

# BridgeAfford：弥合查询-目标差距以实现可泛化的3D Affordance Grounding

::: v-pre
> 原文链接：[BridgeAfford: Bridging Query-Target Gap for Generalizable 3D Affordance Grounding](https://arxiv.org/abs/2610.21918)（arXiv 2610.21918 · 发布日期：2026-10-15）

**BridgeAfford: Bridging Query-Target Gap for Generalizable 3D Affordance Grounding**

针对未见物体3D功能区域定位泛化差的问题，BridgeAfford通过区域对齐与视觉证据聚合，在LASO和PIAD上验证有效。

## 核心要点

- 问题源于查询意图特征与目标区域特征存在语义差距，导致未见物体定位不准。
- IRA在训练中促进几何相似交互区域的跨物体对齐，增强未见结构识别。
- VEA利用2D affordance模型细化注意力分布，引导查询更贴近正确目标区域。
- 在LASO和PIAD数据集上，BridgeAfford优于现有方法，尤其提升未见物体表现。

**验证范围与局限**：验证范围为LASO和PIAD数据集上的实验，摘要未说明真机或物理交互验证。

## 英文摘要 (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.

作者：Yijie Su, Yakun Zhu, Yi Bin, Pengpeng Zeng, Liang Chen, Guoqing Wang, Jingkuan Song, Heng Tao Shen
:::

## 原始参考来源 (Sources)

- [arXiv 2610.21918：BridgeAfford: Bridging Query-Target Gap for Generalizable 3D Affordance Grounding](https://arxiv.org/abs/2610.21918)