Sparse-Up: Learnable Sparse Upsampling for 3D Generation with High-Fidelity Textures
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914061649707008 |
|---|---|
| author | Xiao, Lu Zhang, Jiale Liu, Yang Huang, Taicheng Tian, Xin |
| author_facet | Xiao, Lu Zhang, Jiale Liu, Yang Huang, Taicheng Tian, Xin |
| contents | The creation of high-fidelity 3D assets is often hindered by a 'pixel-level pain point': the loss of high-frequency details. Existing methods often trade off one aspect for another: either sacrificing cross-view consistency, resulting in torn or drifting textures, or remaining trapped by the resolution ceiling of explicit voxels, forfeiting fine texture detail. In this work, we propose Sparse-Up, a memory-efficient, high-fidelity texture modeling framework that effectively preserves high-frequency details. We use sparse voxels to guide texture reconstruction and ensure multi-view consistency, while leveraging surface anchoring and view-domain partitioning to break through resolution constraints. Surface anchoring employs a learnable upsampling strategy to constrain voxels to the mesh surface, eliminating over 70% of redundant voxels present in traditional voxel upsampling. View-domain partitioning introduces an image patch-guided voxel partitioning scheme, supervising and back-propagating gradients only on visible local patches. Through these two strategies, we can significantly reduce memory consumption during high-resolution voxel training without sacrificing geometric consistency, while preserving high-frequency details in textures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_23646 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Sparse-Up: Learnable Sparse Upsampling for 3D Generation with High-Fidelity Textures Xiao, Lu Zhang, Jiale Liu, Yang Huang, Taicheng Tian, Xin Computer Vision and Pattern Recognition The creation of high-fidelity 3D assets is often hindered by a 'pixel-level pain point': the loss of high-frequency details. Existing methods often trade off one aspect for another: either sacrificing cross-view consistency, resulting in torn or drifting textures, or remaining trapped by the resolution ceiling of explicit voxels, forfeiting fine texture detail. In this work, we propose Sparse-Up, a memory-efficient, high-fidelity texture modeling framework that effectively preserves high-frequency details. We use sparse voxels to guide texture reconstruction and ensure multi-view consistency, while leveraging surface anchoring and view-domain partitioning to break through resolution constraints. Surface anchoring employs a learnable upsampling strategy to constrain voxels to the mesh surface, eliminating over 70% of redundant voxels present in traditional voxel upsampling. View-domain partitioning introduces an image patch-guided voxel partitioning scheme, supervising and back-propagating gradients only on visible local patches. Through these two strategies, we can significantly reduce memory consumption during high-resolution voxel training without sacrificing geometric consistency, while preserving high-frequency details in textures. |
| title | Sparse-Up: Learnable Sparse Upsampling for 3D Generation with High-Fidelity Textures |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.23646 |