Arbor: Explicit Geometric Conditioning for Controllable 3D Asset Generation

Hugging Face Daily Papers Papers
3d-generation geometric-conditioning latent-generation controllable-generation constraint-meshes text-to-3d

Summary

Arbor introduces explicit geometric control for 3D asset generation by using constraint meshes (hull, avoidance, touch regions) to condition latent generation, improving spatial constraint adherence without sacrificing object quality.

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.
Original Article
View Cached Full Text

Cached at: 06/23/26, 01:43 PM

Paper page - Arbor: Explicit Geometric Conditioning for Controllable 3D Asset Generation

Source: https://huggingface.co/papers/2606.23514

Abstract

Arbor enables explicit 3D spatial control in text-conditioned latent generation through constraint meshes that define occupancy, avoidance, and contact regions, maintaining object quality while improving constraint adherence.

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 fortext conditioned latent 3D generation. Arbor introducesconstraint meshesas a native 3D control interface. The interface useshull regionswhere geometry should exist,avoidance regionsthat should remain empty, andtouch regionsthe 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 convertingconstraint meshesinto tokens and learning a routed attachment inside a frozendenoiser. Eachlatent regioncan 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 improvesconstraint obediencewhile preservingobject qualityandvariationunder fixed constraints.

View arXiv pageView PDFProject pageGitHub2Add to collection

Get this paper in your agent:

hf papers read 2606\.23514

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.23514 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.23514 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.23514 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Arbor: Tree Search as a Cognition Layer for Autonomous Agents

arXiv cs.AI

Arbor introduces structured tree search as a cognition layer for autonomous agents, enabling multi-day, full-stack LLM inference optimization with up to 193% throughput-latency improvement over vendor baselines through a checks-and-balances multi-agent architecture.

Toward Generalist Autonomous Research via Hypothesis-Tree Refinement

Hugging Face Daily Papers

Arbor is an AI framework for autonomous scientific research that uses a coordinator, executors, and a persistent hypothesis tree to iteratively improve research outcomes across multiple domains, achieving strong results on six real research tasks.

Memory-Augmented Reinforcement Learning Agent for CAD Generation

arXiv cs.AI

This paper proposes a memory-augmented reinforcement learning framework for CAD generation agents that integrates geometric kernel toolchains, dual-track memory, and dynamic utility retrieval to handle complex CAD models with long operation sequences and geometric constraints, achieving improved success rate and geometric consistency.