ChangingGrounding：变化场景中的3D视觉定位
ChangingGrounding: 3D Visual Grounding in Changing Scenes
AI总结：
针对变化场景中3D视觉定位问题，提出首个基准ChangingGrounding及零样本方法Mem-ChangingGrounder，通过记忆检索与多视图融合实现高精度定位并降低探索成本。
摘要：
现实世界中的机器人根据自然语言指令定位物体时，周围的场景在不断变化。然而，现有的大多数3D视觉定位（3DVG）方法仍然假设有一个重建且最新的点云，这种假设迫使进行昂贵的重新扫描并阻碍部署。我们认为3DVG应被表述为一个主动的、记忆驱动的问题，并引入了ChangingGrounding，这是第一个明确衡量智能体在变化场景中利用过去观察、仅在需要时探索、并仍能提供精确3D边界框能力的基准。为了设定一个强参考点，我们还提出了Mem-ChangingGrounder，一种用于此任务的零样本方法，它结合了跨模态检索与轻量级多视图融合：它识别查询隐含的对象类型，检索相关记忆以指导行动，然后在场景中高效地探索目标，当先前操作无效时进行回退，对目标执行多视图扫描，并将多视图扫描的融合证据投影以获得准确的物体边界框。我们在ChangingGrounding上评估了不同的基线，我们的Mem-ChangingGrounder在大幅降低探索成本的同时实现了最高的定位精度。我们希望这一基准和方法能推动面向实际应用的、以记忆为中心的3DVG研究转变。项目页面：https://hm123450.github.io/CGB/。
英文摘要：
Real-world robots localize objects from natural-language instructions while scenes around them keep changing. Yet most of the existing 3D visual grounding (3DVG) method still assumes a reconstructed and up-to-date point cloud, an assumption that forces costly re-scans and hinders deployment. We argue that 3DVG should be formulated as an active, memory-driven problem, and we introduce ChangingGrounding, the first benchmark that explicitly measures how well an agent can exploit past observations, explore only where needed, and still deliver precise 3D boxes in changing scenes. To set a strong reference point, we also propose Mem-ChangingGrounder, a zero-shot method for this task that marries cross-modal retrieval with lightweight multi-view fusion: it identifies the object type implied by the query, retrieves relevant memories to guide actions, then explores the target efficiently in the scene, falls back when previous operations are invalid, performs multi-view scanning of the target, and projects the fused evidence from multi-view scans to get accurate object bounding boxes. We evaluate different baselines on ChangingGrounding, and our Mem-ChangingGrounder achieves the highest localization accuracy while greatly reducing exploration cost. We hope this benchmark and method catalyze a shift toward practical, memory-centric 3DVG research for real-world applications. Project page: https://hm123450.github.io/CGB/ .
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
