Arbor: Explicit Geometric Conditioning for Controllable 3D Asset Generation

2026-06-22

AI Summary

Existing text- or image-conditioned 3D generation models struggle to explicitly express user intent regarding spatial regions an object should occupy or avoid. To address this limitation, this work proposes Arbor—a trainable plug-in module that, for the first time, introduces locally typed geometric constraint grids (specifying presence, avoidance, and contact zones) as non-target evidence into latent 3D diffusion models. Arbor learns to inject these geometric constraints positionally within a frozen denoiser via a constraint-to-token transformation and a spatial routing attention mechanism, enabling fine-grained control over the generated object’s spatial layout. Experiments demonstrate that Arbor significantly improves adherence to spatial constraints in both automatic and human evaluations, without requiring specialized compliance losses, while preserving generation quality and diversity under fixed constraints.

Abstract

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. In authoring, this spatial intent is often known before generation starts. A chair should fit a seating envelope, a prop should leave clearance for motion, or a part should expose a contact surface. Prompts and image views are poor carriers for such constraints, requiring the need for an explicit control interface. We present Arbor, a trainable attachment for text conditioned latent 3D generation. Arbor introduces constraint meshes as a native 3D control interface. The interface uses hull regions where geometry should exist, avoidance regions that should remain empty, and touch regions the object should contact. Unlike completion or whole object scaffold control, these meshes are not target evidence. They are local typed requirements and can include regions where no surface should appear. Arbor keeps this signal as geometry by converting constraint meshes into tokens and learning a routed attachment inside a frozen denoiser. Each latent region can therefore receive the part of the constraint that matters for its spatial location. We evaluate Arbor on automatic and artist curated control benchmarks with hull, avoidance, and touch constraints, and compare the metric trends to a user preference study. Even without dedicated compliance losses, Arbor improves constraint obedience while preserving object quality and variation under fixed constraints.

Problem

• 3D generation
• spatial control
• geometric constraints
• controllable generation
• constraint specification

Innovation

• explicit geometric conditioning
• constraint meshes
• controllable 3D generation
• latent 3D diffusion
• spatial intent