分支中心分词与测试时增强用于骨架生成

中文摘要 AI 辅助

自动骨架生成涉及预测关节位置和骨骼连接性。然而，现有方法在将分支结构编码为令牌序列方面存在困难，并且未能有效利用测试时的计算。我们在一个统一的自回归框架内研究这些选择。首先，我们引入了分支中心分词，这是一种分支感知的表示方法，它将结构相关的元素放在相邻位置，并直接在序列中编码连接性。与标准的BFS风格序列化相比，这种表示产生了更紧凑的序列。其次，我们引入了视图增强生成，这是一种测试时增强过程，对输入网格应用轴对齐旋转，将所有预测映射回一个公共坐标系，并根据不同视图预测之间的网格覆盖率和一致性选择最终骨架。实验表明，我们的方法在骨架预测准确性上优于现有最先进的方法。特别是，在Articulation-XL2.0数据集上，与最强的直接可比基线Auto-Connect相比，我们的方法将CD-J2B误差降低了16.9%。对野外网格的定性结果进一步证明了在不同输入上的泛化能力。

英文摘要

Automatic skeleton generation involves predicting both joint positions and skeletal connectivity. However, existing approaches struggle to encode branch structures into token sequences and do not use test-time computation effectively. We study these choices within a unified autoregressive framework. First, we introduce branch-centric tokenization, a branch-aware representation that places structurally related elements next to each other and encodes connectivity directly in the sequence. Compared with standard BFS-style serialization, this representation yields more compact sequences. Second, we introduce view-augmented generation, a test-time augmentation procedure that applies axis-aligned rotations to the input mesh, maps all predictions back to a common frame, and selects the final skeleton based on mesh coverage and consistency among predictions from different views. Experiments show that our method achieves better skeleton prediction accuracy than state-of-the-art methods. In particular, our method reduces the CD-J2B error by 16.9% on the Articulation-XL2.0 dataset compared to the strongest directly comparable baseline, Auto-Connect. Qualitative results on in-the-wild meshes further demonstrate generalization across diverse inputs.

发表机构

• Purdue University（普渡大学）
• Meshy AI

机构由 AI 辅助整理，请以论文原文为准。