Branch-Centric Tokenization and Test-Time Augmentation for Skeleton Generation

2026-09-05

AI Summary

该研究解决了自动骨架生成中分支结构编码和测试时计算效率问题，通过引入以分支为中心的标记化和视图增强生成方法提高了预测准确性。

Abstract

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.

Problem

• skeleton generation
• branch structures
• token sequences
• test-time computation

Innovation

• branch-centric tokenization
• view-augmented generation
• autoregressive framework