3DAffordSplat：基于3D高斯的高效可用性推理
3DAffordSplat: Efficient Affordance Reasoning with 3D Gaussians
AI总结：
针对3D可用性推理中稀疏点云方法泛化性与鲁棒性不足的问题，提出首个面向3D高斯溅射（3DGS）的大规模多模态数据集3DAffordSplat，并设计含跨模态结构对齐模块的AffordSplatNet模型，提升可用性识别精度与泛化能力。
摘要：
3D可用性推理在将人类指令与3D对象的功能区域关联方面至关重要，有助于具身AI中精准、面向任务的操作。然而，当前主要依赖稀疏3D点云的方法，因对坐标变化敏感及数据固有稀疏性，泛化性和鲁棒性有限。相比之下，3D高斯溅射（3DGS）通过将场景表示为密集连续分布，实现高保真、实时渲染且计算开销极小。这使3DGS成为捕捉细粒度可用性细节、提升识别精度的高效方法。不过，由于缺乏大规模、针对3DGS的可用性数据集，其全部潜力尚未充分挖掘。为克服这些局限，我们提出3DAffordSplat——首个面向3DGS可用性推理的大规模多模态数据集，包含23,677个高斯实例、8,354个点云实例及6,631个人工标注的可用性标签，覆盖21个对象类别和18种可用性类型。基于该数据集，我们引入AffordSplatNet，这是专为3DGS表示可用性推理设计的新型模型，其创新的跨模态结构对齐模块利用结构一致性先验对齐3D点云和3DGS表示，提升可用性识别精度。大量实验表明，3DAffordSplat数据集显著推动3DGS领域的可用性学习，而AffordSplatNet在可见与不可见场景中均持续优于现有方法，凸显其强大的泛化能力。
英文摘要：
3D affordance reasoning is essential in associating human instructions with the functional regions of 3D objects, facilitating precise, task-oriented manipulations in embodied AI. However, current methods, which predominantly depend on sparse 3D point clouds, exhibit limited generalizability and robustness due to their sensitivity to coordinate variations and the inherent sparsity of the data. By contrast, 3D Gaussian Splatting (3DGS) delivers high-fidelity, real-time rendering with minimal computational overhead by representing scenes as dense, continuous distributions. This positions 3DGS as a highly effective approach for capturing fine-grained affordance details and improving recognition accuracy. Nevertheless, its full potential remains largely untapped due to the absence of large-scale, 3DGS-specific affordance datasets. To overcome these limitations, we present 3DAffordSplat, the first large-scale, multi-modal dataset tailored for 3DGS-based affordance reasoning. This dataset includes 23,677 Gaussian instances, 8,354 point cloud instances, and 6,631 manually annotated affordance labels, encompassing 21 object categories and 18 affordance types. Building upon this dataset, we introduce AffordSplatNet, a novel model specifically designed for affordance reasoning using 3DGS representations. AffordSplatNet features an innovative cross-modal structure alignment module that exploits structural consistency priors to align 3D point cloud and 3DGS representations, resulting in enhanced affordance recognition accuracy. Extensive experiments demonstrate that the 3DAffordSplat dataset significantly advances affordance learning within the 3DGS domain, while AffordSplatNet consistently outperforms existing methods across both seen and unseen settings, highlighting its robust generalization capabilities.
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。
