ART：铰接重建 Transformer
ART: Articulated Reconstruction Transformer
把铰接物体拆成刚体部件、用可学习 part slot 从稀疏多状态 RGB 一次性前馈回归几何、纹理与显式关节参数，可直接导出到仿真器，为机器人操作与可交互资产构建提供了免优化的重建范式。
原文依据 reconstructs complete 3D articulated objects from only sparse, multi-state RGB images
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出 ART，即铰接重建 Transformer——一个与类别无关的前馈模型，仅从稀疏的多状态 RGB 图像重建完整的铰接三维物体。此前的铰接物体重建方法要么依赖缓慢的优化过程与脆弱的跨状态对应关系，要么使用仅限于特定物体类别的前馈模型。相比之下，ART 将铰接物体视为刚体部件的组合，把重建表述为基于部件的预测问题。我们新设计的 Transformer 架构将稀疏图像输入映射为一组可学习的部件槽，ART 由此联合解码各个部件的统一表示，包括其三维几何、纹理以及显式的关节参数。所得重建结果具有物理可解释性，并可方便地导出为标准仿真格式。ART 在大规模、多样化的数据集上以逐部件监督进行训练，并在多个基准上评估，相较现有基线取得显著提升，确立了从图像输入进行铰接物体重建的新最优水平。
英文原文摘要 1159 字符
We introduce ART, Articulated Reconstruction Transformer--a category-agnostic, feed-forward model that reconstructs complete 3D articulated objects from only sparse, multi-state RGB images. Previous methods for articulated object reconstruction either rely on slow optimization with fragile cross-state correspondences or use feed-forward models limited to specific object categories. In contrast, ART treats articulated objects as assemblies of rigid parts, formulating reconstruction as a part-based prediction problem. Our newly designed transformer architecture maps sparse image inputs to a set of learnable part slots, from which ART jointly decodes unified representations for individual parts, including their 3D geometry, texture, and explicit articulation parameters. The resulting reconstructions are physically interpretable and readily exportable to standard simulation formats. Trained on a large-scale, diverse dataset with per-part supervision, and evaluated across diverse benchmarks, ART achieves significant improvements over existing baselines and establishes a new state of the art for articulated object reconstruction from image inputs.