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

Native 3D generative models have achieved remarkable x001C-delity and speed, yet they sux001Ber from a critical limitation: inability toprescribe precise structural articulations, where precise structural con-trol within the native 3D space remains underexplored. This paper pro-poses SK-Adapter, a simple yet ex001Ecient and ex001Bective framework thatunlocks precise skeletal manipulation for native 3D generation. Mov-ing beyond text or image prompts, which can be ambiguous for precisestructure, we treat the 3D skeleton as a x001Crst-class control signal. SK-Adapter is a lightweight structural adapter network that encodes jointcoordinates and topology into learnable tokens, which are injected intothe frozen 3D generation backbone via cross-attention. This design al-lows the model to not only ex001Bectively x0010attendx0011 to specix001Cc 3D structuralconstraints but also preserve its original generative priors. To bridgethe data gap, we contribute the Objaverse-TMS dataset, a large-scale⋆ „Equal contribution. Equal advising.dataset of 24k text-mesh-skeleton pairs. Extensive experiments conx001Crmthat our method achieves robust structural control while preserving thegeometry and texture quality of the foundation model, signix001Ccantly out-performing existing baselines. Furthermore, we extend this capability tolocal 3D editing, enabling region-specix001Cc editing of existing assets withskeletal guidance, which is unattainable by previous methods. Projectpage: https://sk-adapter.github.io/