基于2D引导与几何优化的任务感知3D可供性分割
Task-Aware 3D Affordance Segmentation via 2D Guidance and Geometric Refinement
AI总结：
针对现有3D场景级可供性分割方法忽略点云几何信息、计算成本高的问题，本文提出由粗到精的TASA框架，融合2D语义引导与3D几何优化，在SceneFun3D上实现了精度与效率的双重提升。
摘要：
从自然语言指令理解3D场景级可供性，是让具身智能体在复杂环境中开展有意义交互的核心基础。但该任务因需要语义推理与空间对齐仍存在较高难度，现有方法多聚焦物体级可供性，或仅将2D预测直接升维到3D空间，忽略了点云中丰富的几何结构信息，且会产生较高计算开销。为解决上述局限，本文提出任务感知3D场景级可供性分割框架TASA，这一新型几何优化框架以由粗到精的方式联合利用2D语义线索与3D几何推理。为提升可供性检测效率，TASA设置任务感知2D可供性检测模块，从语言和视觉输入中识别可操作点，引导筛选任务相关视图；为充分挖掘3D几何信息，提出3D可供性优化模块，将2D语义先验与局部3D几何信息融合，生成精准、空间连贯的3D可供性掩码。在SceneFun3D数据集上的实验表明，TASA在场景级可供性分割任务的精度与效率上均显著优于基线方法。
英文摘要：
Understanding 3D scene-level affordances from natural language instructions is essential for enabling embodied agents to interact meaningfully in complex environments. However, this task remains challenging due to the need for semantic reasoning and spatial grounding. Existing methods mainly focus on object-level affordances or merely lift 2D predictions to 3D, neglecting rich geometric structure information in point clouds and incurring high computational costs. To address these limitations, we introduce Task-Aware 3D Scene-level Affordance segmentation (TASA), a novel geometry-optimized framework that jointly leverages 2D semantic cues and 3D geometric reasoning in a coarse-to-fine manner. To improve the affordance detection efficiency, TASA features a task-aware 2D affordance detection module to identify manipulable points from language and visual inputs, guiding the selection of task-relevant views. To fully exploit 3D geometric information, a 3D affordance refinement module is proposed to integrate 2D semantic priors with local 3D geometry, resulting in accurate and spatially coherent 3D affordance masks. Experiments on SceneFun3D demonstrate that TASA significantly outperforms the baselines in both accuracy and efficiency in scene-level affordance segmentation.
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。
