TexSpot: 3D Texture Enhancement with Spatially-uniform Point Latent Representation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915797713027072 |
|---|---|
| author | Lu, Ziteng Wu, Yushuang Ye, Chongjie Qiu, Yuda Shao, Jing Guo, Xiaoyang Zhou, Jiaqing Hu, Tianlei Zhou, Kun Han, Xiaoguang |
| author_facet | Lu, Ziteng Wu, Yushuang Ye, Chongjie Qiu, Yuda Shao, Jing Guo, Xiaoyang Zhou, Jiaqing Hu, Tianlei Zhou, Kun Han, Xiaoguang |
| contents | High-quality 3D texture generation remains a fundamental challenge due to the view-inconsistency inherent in current mainstream multi-view diffusion pipelines. Existing representations either rely on UV maps, which suffer from distortion during unwrapping, or point-based methods, which tightly couple texture fidelity to geometric density that limits high-resolution texture generation. To address these limitations, we introduce TexSpot, a diffusion-based texture enhancement framework. At its core is Texlet, a novel 3D texture representation that merges the geometric expressiveness of point-based 3D textures with the compactness of UV-based representation. Each Texlet latent vector encodes a local texture patch via a 2D encoder and is further aggregated using a 3D encoder to incorporate global shape context. A cascaded 3D-to-2D decoder reconstructs high-quality texture patches, enabling the Texlet space learning. Leveraging this representation, we train a diffusion transformer conditioned on Texlets to refine and enhance textures produced by multi-view diffusion methods. Extensive experiments demonstrate that TexSpot significantly improves visual fidelity, geometric consistency, and robustness over existing state-of-the-art 3D texture generation and enhancement approaches. Project page: https://texlet-arch.github.io/TexSpot-page. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_12157 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TexSpot: 3D Texture Enhancement with Spatially-uniform Point Latent Representation Lu, Ziteng Wu, Yushuang Ye, Chongjie Qiu, Yuda Shao, Jing Guo, Xiaoyang Zhou, Jiaqing Hu, Tianlei Zhou, Kun Han, Xiaoguang Computer Vision and Pattern Recognition Graphics High-quality 3D texture generation remains a fundamental challenge due to the view-inconsistency inherent in current mainstream multi-view diffusion pipelines. Existing representations either rely on UV maps, which suffer from distortion during unwrapping, or point-based methods, which tightly couple texture fidelity to geometric density that limits high-resolution texture generation. To address these limitations, we introduce TexSpot, a diffusion-based texture enhancement framework. At its core is Texlet, a novel 3D texture representation that merges the geometric expressiveness of point-based 3D textures with the compactness of UV-based representation. Each Texlet latent vector encodes a local texture patch via a 2D encoder and is further aggregated using a 3D encoder to incorporate global shape context. A cascaded 3D-to-2D decoder reconstructs high-quality texture patches, enabling the Texlet space learning. Leveraging this representation, we train a diffusion transformer conditioned on Texlets to refine and enhance textures produced by multi-view diffusion methods. Extensive experiments demonstrate that TexSpot significantly improves visual fidelity, geometric consistency, and robustness over existing state-of-the-art 3D texture generation and enhancement approaches. Project page: https://texlet-arch.github.io/TexSpot-page. |
| title | TexSpot: 3D Texture Enhancement with Spatially-uniform Point Latent Representation |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2602.12157 |