SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909555380715520 |
|---|---|
| author | He, Xianglong Zou, Zi-Xin Chen, Chia-Hao Guo, Yuan-Chen Liang, Ding Yuan, Chun Ouyang, Wanli Cao, Yan-Pei Li, Yangguang |
| author_facet | He, Xianglong Zou, Zi-Xin Chen, Chia-Hao Guo, Yuan-Chen Liang, Ding Yuan, Chun Ouyang, Wanli Cao, Yan-Pei Li, Yangguang |
| contents | Creating high-fidelity 3D meshes with arbitrary topology, including open surfaces and complex interiors, remains a significant challenge. Existing implicit field methods often require costly and detail-degrading watertight conversion, while other approaches struggle with high resolutions. This paper introduces SparseFlex, a novel sparse-structured isosurface representation that enables differentiable mesh reconstruction at resolutions up to $1024^3$ directly from rendering losses. SparseFlex combines the accuracy of Flexicubes with a sparse voxel structure, focusing computation on surface-adjacent regions and efficiently handling open surfaces. Crucially, we introduce a frustum-aware sectional voxel training strategy that activates only relevant voxels during rendering, dramatically reducing memory consumption and enabling high-resolution training. This also allows, for the first time, the reconstruction of mesh interiors using only rendering supervision. Building upon this, we demonstrate a complete shape modeling pipeline by training a variational autoencoder (VAE) and a rectified flow transformer for high-quality 3D shape generation. Our experiments show state-of-the-art reconstruction accuracy, with a ~82% reduction in Chamfer Distance and a ~88% increase in F-score compared to previous methods, and demonstrate the generation of high-resolution, detailed 3D shapes with arbitrary topology. By enabling high-resolution, differentiable mesh reconstruction and generation with rendering losses, SparseFlex significantly advances the state-of-the-art in 3D shape representation and modeling. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_21732 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling He, Xianglong Zou, Zi-Xin Chen, Chia-Hao Guo, Yuan-Chen Liang, Ding Yuan, Chun Ouyang, Wanli Cao, Yan-Pei Li, Yangguang Computer Vision and Pattern Recognition Creating high-fidelity 3D meshes with arbitrary topology, including open surfaces and complex interiors, remains a significant challenge. Existing implicit field methods often require costly and detail-degrading watertight conversion, while other approaches struggle with high resolutions. This paper introduces SparseFlex, a novel sparse-structured isosurface representation that enables differentiable mesh reconstruction at resolutions up to $1024^3$ directly from rendering losses. SparseFlex combines the accuracy of Flexicubes with a sparse voxel structure, focusing computation on surface-adjacent regions and efficiently handling open surfaces. Crucially, we introduce a frustum-aware sectional voxel training strategy that activates only relevant voxels during rendering, dramatically reducing memory consumption and enabling high-resolution training. This also allows, for the first time, the reconstruction of mesh interiors using only rendering supervision. Building upon this, we demonstrate a complete shape modeling pipeline by training a variational autoencoder (VAE) and a rectified flow transformer for high-quality 3D shape generation. Our experiments show state-of-the-art reconstruction accuracy, with a ~82% reduction in Chamfer Distance and a ~88% increase in F-score compared to previous methods, and demonstrate the generation of high-resolution, detailed 3D shapes with arbitrary topology. By enabling high-resolution, differentiable mesh reconstruction and generation with rendering losses, SparseFlex significantly advances the state-of-the-art in 3D shape representation and modeling. |
| title | SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.21732 |