发表机构
Interdisciplinary Program in AI, Seoul National University; Artificial Intelligence Institute, Seoul National University; Department of Computer Science, Seoul National University（首尔国立大学人工智能跨学科项目; 首尔国立大学人工智能研究所; 首尔国立大学计算机科学系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对物流自动化中未见物体分割难题，提出基于可变形注意力的RGB-D融合Transformer（DA-Fusion），结合RGB与深度数据优势提升分割精度，引入OCBD数据集，实验证明其性能优于现有方法，适用于现实物流任务。
AI 中文摘要
在物流自动化中，对未见物体进行精确分割对于在杂乱环境中的高效机器人操作至关重要。诸如箱式拾取和货架拾取等任务需要强大的感知能力来处理遮挡、不同的物体形状和复杂的空间布局。传统基于RGB的方法因依赖纹理往往过度分割物体，而基于深度的方法常因主要关注几何特征而分割不足。为解决这些局限，我们提出DA-Fusion，一种基于可变形注意力的RGB-D融合Transformer用于未见物体实例分割。它有效结合了RGB和深度数据的优势，提高了在杂乱和多层物体环境中的分割精度。我们还引入了物体杂乱箱数据集（OCBD），一个专门为评估自上而下视图中的箱式拾取场景而定制的基准数据集。广泛评估表明，DA-Fusion在各种环境中均优于现有方法，特别适用于现实世界的物流任务。
英文摘要
In logistics automation, precise segmentation of unseen objects is crucial for efficient robotic manipulation in cluttered environments. Tasks such as bin-picking and shelf-picking require robust perception to handle occlusions, varying object shapes, and complex spatial arrangements. Traditional RGB-based methods tend to over-segment objects due to their reliance on texture, while depth-based methods often under-segment by focusing primarily on geometric features. To address these limitations, we propose DA-Fusion, a deformable attention-based RGB-D fusion Transformer designed for unseen object instance segmentation. DA-Fusion effectively combines the strengths of both RGB and depth data, enhancing segmentation accuracy in cluttered and multi-layered object environments. We also introduce the Object Clutter Bin Dataset (OCBD), a benchmark dataset specifically tailored for evaluating bin-picking scenarios in top-down views. Extensive evaluations demonstrate that DA-Fusion outperforms state-of-the-art methods across diverse environments, making it particularly suited for real-world logistics tasks.
Comments7 pages, 5 figures. Published in the Proceedings of the 2025 IEEE International Conference on Robotics and Automation (ICRA 2025)
Journal ref2025 IEEE International Conference on Robotics and Automation (ICRA), 2025, pp. 7490-7496
DOI：10.1109/ICRA55743.2025.11128151
