发表机构
UCLA; University of Osaka（加利福尼亚大学洛杉矶分校; 大阪大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对自回归绑定模型在植物骨骼重建中存在的问题，通过多轮微调优化UniRig模型，实现了跨多种植物形态的泛化，为自动化植物绑定提供了可行方案。
AI 中文摘要
自回归绑定模型如UniRig和SkinTokens在铰接角色上表现良好，但它们对植物结构的泛化能力在很大程度上尚未被探索，因为植物拓扑结构呈现出高度可变的非典型分支模式，这对学习到的骨骼先验提出了挑战。我们使用合成L系统生成的树木以及涵盖单轴、合轴、轮生和藤本原型的真实扫描数据，评估这些模型用于植物骨骼重建的性能。初步测试显示，UniRig会将复杂分支坍缩为近线性链，而SkinTokens能更好地保留拓扑结构，但会过度分割分支并产生不稳定的输出空间，因此我们选择UniRig进行研究，因其稳定性更高。诊断结果显示，坍缩源于采样层对分支token的抑制，进一步分析表明，冻结的网格编码器对结构变化的敏感性有限，这指向了分词流程中的几何瓶颈，而非纯粹的学习偏差。基于这些发现，我们在多个程序生成的合成数据集上应用多轮微调。经过多轮训练，模型逐步恢复了准确的分支拓扑结构，并泛化到仅含分支之外的带叶植物，考虑到叶片具有零厚度、依赖网格法向的几何特性，这是更具挑战性的情况。所得模型在不同植物形态上表现出良好的泛化能力，且未进行叶片特定的架构改动，这表明针对性微调可大幅缩小角色绑定先验与植物骨骼结构之间的领域差距。因此，我们的工作为实现涵盖分支拓扑和叶片类型的自动化植物绑定提供了可行路径，甚至适用于本研究未涉及的类型。
英文摘要
Autoregressive rigging models such as UniRig and SkinTokens perform well on articulated characters, but their ability to generalize to plant structures remains largely unexplored, since plant topologies exhibit highly variable, non-canonical branching patterns that challenge learned skeletal priors. We evaluate these models for plant skeletal reconstruction using synthetic L-system-generated trees and real scanned data spanning monopodial, sympodial, whorled, and vine-like archetypes. Preliminary testing showed UniRig collapsing complex branching into near-linear chains, while SkinTokens preserved topology better but over-segmented branches and produced an unstable output space, so we focused on UniRig for its greater stability. Diagnosis traced the collapse to sampling-level suppression of branch tokens, and further analysis showed the frozen mesh encoder had limited sensitivity to structural variation, pointing to a geometric bottleneck in the tokenization pipeline rather than a purely learned bias. Building on these findings, we applied multi-round fine-tuning over multiple procedurally generated synthetic datasets. Across rounds, the model progressively recovered accurate branching topology and generalized beyond branch-only structures to plants with foliage, a harder case given the zero-thickness, mesh-normal-dependent geometry of leaves. The resulting model generalized well across diverse plant forms without leaf-specific architectural changes, indicating that targeted fine-tuning can substantially close the domain gap between character-rigging priors and plant skeletal structure. As such, our work points toward a viable path for automated plant rigging across both branch topology and foliage type, even those not considered in our findings.
