SpaceControl: Introducing Test-Time Spatial Control to 3D Generative Modeling

TL;DR

SpaceControl is a training-free, test-time method that provides intuitive spatial control over 3D generative models, allowing precise manipulation of object geometry without additional training.

Contribution

It introduces a novel test-time approach for explicit spatial control in 3D generation that accepts diverse geometric inputs and integrates seamlessly with existing models.

Findings

Outperforms baselines in geometric faithfulness

Maintains high visual quality

Enables real-time interactive editing

Abstract

Generative methods for 3D assets have recently achieved remarkable progress, yet providing intuitive and precise control over the object geometry remains a key challenge. Existing approaches predominantly rely on text or image prompts, which often fall short in geometric specificity: language can be ambiguous, and images are difficult to manipulate. In this work, we introduce SpaceControl, a training-free test-time method for explicit spatial control of 3D asset generation. Our approach accepts a wide range of geometric inputs, from coarse primitives to detailed meshes, and integrates seamlessly with modern generative models without requiring any additional training. A control parameter lets users trade off between geometric fidelity and output realism. Extensive quantitative evaluation and user studies demonstrate that SpaceControl outperforms both training-based and optimization-based baselines in geometric faithfulness while preserving high visual quality. Finally, we present an interactive interface for real-time superquadric editing and direct 3D asset generation, enabling seamless use in creative workflows. Project page: https://spacecontrol3d.github.io/.