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

TL;DR

SK-Adapter introduces a skeletal control framework for native 3D generation, enabling precise structural manipulation and local editing, while maintaining high quality and leveraging a new large-scale dataset.

Contribution

The paper presents SK-Adapter, a lightweight framework for skeletal control in 3D generation, and introduces the Objaverse-TMS dataset for training and evaluation.

Findings

Achieves robust structural control in 3D generation.

Preserves geometry and texture quality of the original models.

Enables local 3D editing with skeletal guidance.

Abstract

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/