OpenGround：基于规划的开放世界3D视觉定位在线感知
OpenGround: Planning-based Online Perception for Open-World 3D Visual Grounding
AI总结：
针对开放世界3D视觉定位中现有方法的局限，提出OpenGround框架，集成任务链规划与上下文引导感知，还构建OpenTarget数据集。实验表明其在多个数据集上性能优异，在开放世界评估中有显著提升。
摘要：
3D视觉定位旨在基于3D场景中的自然语言描述来定位物体。现有监督方法受泛化限制，近期的零样本方法通常依赖预定义对象查找表查询视觉语言模型以单步定位推理物体位置，限制了在目标未定义和复杂查询场景中的应用。为解决这些问题，我们提出OpenGround，一种用于开放世界3D视觉定位的新型零样本框架，它与近期零样本方法兼容。OpenGround集成任务链规划将查询分解为上下文到目标子目标的计划进行渐进式定位，并结合上下文引导感知在任务链的上下文引导下在线感知新物体。我们还提出了新数据集OpenTarget，包含7000多个物体描述对以模拟开放世界评估。大量实验表明，OpenGround在Nr3D上取得有竞争力的性能，在ScanRefer上达到当前最优，在OpenTarget上有17.6%的显著提升。
英文摘要：
3D visual grounding aims to locate objects based on natural language descriptions in 3D scenes. Existing supervised methods are limited by generalization and recent zero-shot methods typically rely on a predefined Object Lookup Table (OLT) to query Visual Language Models (VLMs) for reasoning about object locations via a single step grounding, which limits the applications in scenarios with undefined targets and complex queries. To address these problems, we present OpenGround, a novel zero-shot framework for open-world 3D visual grounding that remains compatible with recent zero-shot methods. OpenGround integrates Task-Chain Planning to decompose a query into a plan of context-to-target sub-goals for progressive grounding, and Context-Guided Perception to perceive novel objects online under context guidance from the task chain. We also propose a new dataset named OpenTarget, which contains over 7000 object-description pairs to mimic open-world evaluation. Extensive experiments demonstrate that OpenGround achieves competitive performance on Nr3D, state-of-the-art on ScanRefer, and delivers a substantial 17.6\% improvement on OpenTarget. Project Page at https://why-102.github.io/openground.io/.
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。
