SpaceControl: Introducing Test-Time Spatial Control to 3D Generative Modeling
This addresses the challenge of ambiguous text or image prompts for 3D asset creation, offering a practical tool for creative workflows, though it is incremental as it builds on existing pre-trained models.
The paper tackles the problem of providing intuitive and precise geometric control in 3D generative modeling by introducing SpaceControl, a training-free test-time method that accepts geometric inputs like primitives or meshes and outperforms baselines in geometric faithfulness while maintaining visual quality.
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 cumbersome to edit. In this work, we introduce SpaceControl, a training-free test-time method for explicit spatial control of 3D generation. Our approach accepts a wide range of geometric inputs, from coarse primitives to detailed meshes, and integrates seamlessly with modern pre-trained generative models without requiring any additional training. A controllable 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 user interface that enables online editing of superquadrics for direct conversion into textured 3D assets, facilitating practical deployment in creative workflows. Find our project page at https://spacecontrol3d.github.io/