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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Fedele, Elisabetta, Engelmann, Francis, Huang, Ian, Litany, Or, Pollefeys, Marc, Guibas, Leonidas
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914391470899200
author Fedele, Elisabetta
Engelmann, Francis
Huang, Ian
Litany, Or
Pollefeys, Marc
Guibas, Leonidas
author_facet Fedele, Elisabetta
Engelmann, Francis
Huang, Ian
Litany, Or
Pollefeys, Marc
Guibas, Leonidas
contents 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/.
format Preprint
id arxiv_https___arxiv_org_abs_2512_05343
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SpaceControl: Introducing Test-Time Spatial Control to 3D Generative Modeling
Fedele, Elisabetta
Engelmann, Francis
Huang, Ian
Litany, Or
Pollefeys, Marc
Guibas, Leonidas
Computer Vision and Pattern Recognition
Artificial Intelligence
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/.
title SpaceControl: Introducing Test-Time Spatial Control to 3D Generative Modeling
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2512.05343