Im2SurfTex: Surface Texture Generation via Neural Backprojection of Multi-View Images
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_ | 1866914191986655232 |
|---|---|
| author | Georgiou, Yiangos Loizou, Marios Averkiou, Melinos Kalogerakis, Evangelos |
| author_facet | Georgiou, Yiangos Loizou, Marios Averkiou, Melinos Kalogerakis, Evangelos |
| contents | We present Im2SurfTex, a method that generates textures for input 3D shapes by learning to aggregate multi-view image outputs produced by 2D image diffusion models onto the shapes' texture space. Unlike existing texture generation techniques that use ad hoc backprojection and averaging schemes to blend multiview images into textures, often resulting in texture seams and artifacts, our approach employs a trained neural module to boost texture coherency. The key ingredient of our module is to leverage neural attention and appropriate positional encodings of image pixels based on their corresponding 3D point positions, normals, and surface-aware coordinates as encoded in geodesic distances within surface patches. These encodings capture texture correlations between neighboring surface points, ensuring better texture continuity. Experimental results show that our module improves texture quality, achieving superior performance in high-resolution texture generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_14006 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Im2SurfTex: Surface Texture Generation via Neural Backprojection of Multi-View Images Georgiou, Yiangos Loizou, Marios Averkiou, Melinos Kalogerakis, Evangelos Graphics We present Im2SurfTex, a method that generates textures for input 3D shapes by learning to aggregate multi-view image outputs produced by 2D image diffusion models onto the shapes' texture space. Unlike existing texture generation techniques that use ad hoc backprojection and averaging schemes to blend multiview images into textures, often resulting in texture seams and artifacts, our approach employs a trained neural module to boost texture coherency. The key ingredient of our module is to leverage neural attention and appropriate positional encodings of image pixels based on their corresponding 3D point positions, normals, and surface-aware coordinates as encoded in geodesic distances within surface patches. These encodings capture texture correlations between neighboring surface points, ensuring better texture continuity. Experimental results show that our module improves texture quality, achieving superior performance in high-resolution texture generation. |
| title | Im2SurfTex: Surface Texture Generation via Neural Backprojection of Multi-View Images |
| topic | Graphics |
| url | https://arxiv.org/abs/2502.14006 |