Learning to Refine Gesture-Derived Voxel-to-Loop for Generative 3D Modeling in VR

Authors

• Kallen Lonbom, Chapman University
• Trudi Di Qi, Chapman UniversityFollow

Document Type

Conference Proceeding

Publication Date

3-26-2026

Abstract

We present a generative modeling pipeline for refining and denoising coarse 3D shapes created through freehand interaction in virtual reality (VR). While recent loop-based generative models focus on shape synthesis from clean inputs, our work addresses the challenge of reconstructing coherent geometry from noisy, coarse volumetric data. To this end, we introduce a hybrid voxel-to-loop representation that captures the topology of rough voxel shapes and converts them into sequential cross-sectional loops for generative refinement. We develop two transformer architectures and evaluate their efficacy primarily on synthetically perturbed datasets with additional examples from VR. Our results demonstrate that this representation is topologically robust to the irregularities of raw input, establishing a technical foundation for future AI-assisted immersive 3D modeling systems.

Comments

This is a pre-copy-editing, author-produced PDF of an article accepted for publication in 2026 IEEE International Conference on Artificial Intelligence and eXtended and Virtual Reality (AIxVR). This article may not exactly replicate the final published version. The definitive publisher-authenticated version is available online at https://doi.org/10.1109/AIxVR67263.2026.00029.

Recommended Citation

K. Lonbom and T. Di Qi, "Learning to Refine Gesture-Derived Voxel-to-Loop for Generative 3D Modeling in VR," 2026 IEEE International Conference on Artificial Intelligence and eXtended and Virtual Reality (AIxVR), Osaka, Japan, 2026, pp. 173-178, https://doi.org/10.1109/AIxVR67263.2026.00029.

Copyright

© 2026 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.