TEXTRIX: Latent Attribute Grid for Native Texture Generation and Beyond
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_ | 1866912743951433728 |
|---|---|
| author | Zeng, Yifei Bao, Yajie Qian, Jiachen Wu, Shuang Lin, Youtian Zhu, Hao Li, Buyu Zhang, Feihu Cao, Xun Yao, Yao |
| author_facet | Zeng, Yifei Bao, Yajie Qian, Jiachen Wu, Shuang Lin, Youtian Zhu, Hao Li, Buyu Zhang, Feihu Cao, Xun Yao, Yao |
| contents | Prevailing 3D texture generation methods, which often rely on multi-view fusion, are frequently hindered by inter-view inconsistencies and incomplete coverage of complex surfaces, limiting the fidelity and completeness of the generated content. To overcome these challenges, we introduce TEXTRIX, a native 3D attribute generation framework for high-fidelity texture synthesis and downstream applications such as precise 3D part segmentation. Our approach constructs a latent 3D attribute grid and leverages a Diffusion Transformer equipped with sparse attention, enabling direct coloring of 3D models in volumetric space and fundamentally avoiding the limitations of multi-view fusion. Built upon this native representation, the framework naturally extends to high-precision 3D segmentation by training the same architecture to predict semantic attributes on the grid. Extensive experiments demonstrate state-of-the-art performance on both tasks, producing seamless, high-fidelity textures and accurate 3D part segmentation with precise boundaries. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_02993 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TEXTRIX: Latent Attribute Grid for Native Texture Generation and Beyond Zeng, Yifei Bao, Yajie Qian, Jiachen Wu, Shuang Lin, Youtian Zhu, Hao Li, Buyu Zhang, Feihu Cao, Xun Yao, Yao Computer Vision and Pattern Recognition Prevailing 3D texture generation methods, which often rely on multi-view fusion, are frequently hindered by inter-view inconsistencies and incomplete coverage of complex surfaces, limiting the fidelity and completeness of the generated content. To overcome these challenges, we introduce TEXTRIX, a native 3D attribute generation framework for high-fidelity texture synthesis and downstream applications such as precise 3D part segmentation. Our approach constructs a latent 3D attribute grid and leverages a Diffusion Transformer equipped with sparse attention, enabling direct coloring of 3D models in volumetric space and fundamentally avoiding the limitations of multi-view fusion. Built upon this native representation, the framework naturally extends to high-precision 3D segmentation by training the same architecture to predict semantic attributes on the grid. Extensive experiments demonstrate state-of-the-art performance on both tasks, producing seamless, high-fidelity textures and accurate 3D part segmentation with precise boundaries. |
| title | TEXTRIX: Latent Attribute Grid for Native Texture Generation and Beyond |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.02993 |