PlantRig - From Bones to Branches: Adaptation of Autoregressive Rigging Models for Plant Skeletal Reconstruction

2026-08-02

AI Summary

Existing autoregressive rigging models struggle to accurately reconstruct the highly variable and non-canonical branching topologies of plants, often resulting in structural distortions or oversimplifications. Building upon the UniRig architecture, this work employs synthetic plant data generated via L-systems for targeted multi-stage fine-tuning, revealing that reconstruction failures stem from the suppression of branch tokens during sampling and the mesh encoder’s insensitivity to structural variations. Without modifying the underlying architecture, the proposed approach effectively bridges the domain gap between character and plant modeling, successfully recovering precise branching topologies—including those with leaves—across diverse plant species. The method demonstrates strong generalization and morphological robustness on real-world scanned data.

Abstract

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.

Problem

• plant skeletal reconstruction
• autoregressive rigging models
• branching topology
• domain generalization
• skeletal priors

Innovation

• autoregressive rigging
• plant skeletal reconstruction
• topology generalization
• procedural fine-tuning
• L-system synthesis