Arbor: Explicit Geometric Conditioning for Controllable 3D Asset Generation

Text and image conditioned 3D models now generate convincing assets, but they still offer little direct control over the space an object should occupy or avoid. We present Arbor, a trainable attachment for text conditioned latent 3D generation. Arbor introduces constraint meshes as a native 3D control interface using hull regions where geometry should exist, avoidance regions that should remain empty, and touch regions the object should contact. Arbor keeps this signal as geometry by converting constraint meshes into tokens and learning a routed attachment inside a frozen denoiser. Even without dedicated compliance losses, Arbor improves constraint obedience while preserving object quality and variation under fixed constraints.