SK-Adapter：面向原生3D生成的骨骼结构控制框架

SK-Adapter: Skeleton-Based Structural Control for Native 3D Generation

March 14, 2026

作者: Anbang Wang, Yuzhuo Ao, Shangzhe Wu, Chi-Keung Tang

cs.AI

摘要

尽管原生三维生成模型在保真度与生成速度方面取得了显著进展，但其存在一个关键缺陷：无法实现精确的结构化关节控制，且在原生三维空间内进行精确结构调控的研究仍处于探索不足的状态。本文提出SK-Adapter这一简洁高效的新型框架，通过解锁骨骼操控能力实现精确控制的原生三维生成。相较于文本或图像提示在精确结构控制上的模糊性，我们将三维骨骼视为首要控制信号。该框架采用轻量化结构适配网络，将关节坐标与拓扑关系编码为可学习令牌，通过交叉注意力机制注入到冻结的三维生成主干网络中。这种巧妙设计使模型既能有效"关注"特定三维结构约束，又能保持原有的生成先验。为弥补数据空白，我们构建了包含2.4万组文本-网格-骨骼对的大规模数据集Objaverse-TMS。大量实验表明，本方法在保持基础模型几何与纹理质量的同时实现了稳健的结构控制，显著优于现有基线模型。此外，我们将该能力拓展至局部三维编辑领域，首次实现基于骨骼引导的现有资产区域化编辑，这是以往方法无法达到的。项目页面：https://sk-adapter.github.io/

English

Native 3D generative models have achieved remarkable fidelity and speed, yet they suffer from a critical limitation: inability to prescribe precise structural articulations, where precise structural control within the native 3D space remains underexplored. This paper proposes SK-Adapter, a simple and yet highly efficient and effective framework that unlocks precise skeletal manipulation for native 3D generation. Moving beyond text or image prompts, which can be ambiguous for precise structure, we treat the 3D skeleton as a first-class control signal. SK-Adapter is a lightweight structural adapter network that encodes joint coordinates and topology into learnable tokens, which are injected into the frozen 3D generation backbone via cross-attention. This smart design allows the model to not only effectively "attend" to specific 3D structural constraints but also preserve its original generative priors. To bridge the data gap, we contribute Objaverse-TMS dataset, a large-scale dataset of 24k text-mesh-skeleton pairs. Extensive experiments confirm that our method achieves robust structural control while preserving the geometry and texture quality of the foundation model, significantly outperforming existing baselines. Furthermore, we extend this capability to local 3D editing, enabling the region specific editing of existing assets with skeletal guidance, which is unattainable by previous methods. Project Page: https://sk-adapter.github.io/