T-FunS3D：任务驱动的分层开放词汇3D功能分割
T-FunS3D: Task-Driven Hierarchical Open-Vocabulary 3D Functionality Segmentation
AI总结：
提出T-FunS3D方法，通过构建开放词汇场景图并利用视觉语言模型，实现任务驱动的分层3D功能分割，在保持性能的同时提升速度和降低内存消耗。
摘要：
开放词汇3D功能分割使机器人能够在3D场景中定位功能性物体组件。这是一项需要空间理解和任务解释的挑战性任务。当前的开放词汇3D分割方法主要关注物体级识别，而场景级部分分割方法试图详尽地分割整个场景，导致资源密集且耗时。在粒度、准确性和速度之间平衡分割性能仍然是一个挑战。作为缓解这一问题的一步，我们引入了T-FunS3D，一种任务驱动的分层开放词汇3D功能分割方法，为机器人应用提供可操作的感知。我们的方法以室内场景的3D点云和带姿态的RGB-D图像作为输入。通过提取环境中的实例及其视觉嵌入，我们构建了一个开放词汇场景图。给定任务描述，T-FunS3D识别场景图中最相关的实例，并利用视觉语言模型定位其功能组件。在SceneFun3D数据集上的实验表明，T-FunS3D在开放词汇3D功能分割方面与最先进方法相当，同时实现了更快的运行时间和更少的内存使用。
英文摘要：
Open-vocabulary 3D functionality segmentation enables robots to localize functional object components in 3D scenes. It is a challenging task that requires spatial understanding and task interpretation. Current open-vocabulary 3D segmentation methods primarily focus on object-level recognition, while scene-wide part segmentation methods attempt to segment the entire scene exhaustively, making them highly resource-intensive and time consuming. Balancing segmentation performance in terms of granularity, accuracy, and speed remains a challenge. As one step towards alleviating this, we introduce T-FunS3D, a task-driven hierarchical open-vocabulary 3D functionality segmentation method that provides actionable perception for robotic applications. Our method takes as input the 3D point cloud and posed RGB-D images of an indoor scene. We construct an open-vocabulary scene graph by extracting instances and their visual embeddings in the environment. Given a task description, T-FunS3D identifies the most relevant instances in the scene graph and locates their functional components leveraging a vision-language model. Experiments on the SceneFun3D dataset demonstrate that T-FunS3D is comparable to state-of-the-art in open-vocabulary 3D functionality segmentation, while achieving faster runtime and reduced memory usage.
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。
