ConTEXTure: Consistent Multiview Images to Texture
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929421197246464 |
|---|---|
| author | Ahn, Jaehoon Cho, Sumin Jung, Harim Hong, Kibeom Ban, Seonghoon Jung, Moon-Ryul |
| author_facet | Ahn, Jaehoon Cho, Sumin Jung, Harim Hong, Kibeom Ban, Seonghoon Jung, Moon-Ryul |
| contents | We introduce ConTEXTure, a generative network designed to create a texture map/atlas for a given 3D mesh using images from multiple viewpoints. The process begins with generating a front-view image from a text prompt, such as 'Napoleon, front view', describing the 3D mesh. Additional images from different viewpoints are derived from this front-view image and camera poses relative to it. ConTEXTure builds upon the TEXTure network, which uses text prompts for six viewpoints (e.g., 'Napoleon, front view', 'Napoleon, left view', etc.). However, TEXTure often generates images for non-front viewpoints that do not accurately represent those viewpoints.To address this issue, we employ Zero123++, which generates multiple view-consistent images for the six specified viewpoints simultaneously, conditioned on the initial front-view image and the depth maps of the mesh for the six viewpoints. By utilizing these view-consistent images, ConTEXTure learns the texture atlas from all viewpoint images concurrently, unlike previous methods that do so sequentially. This approach ensures that the rendered images from various viewpoints, including back, side, bottom, and top, are free from viewpoint irregularities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_10558 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ConTEXTure: Consistent Multiview Images to Texture Ahn, Jaehoon Cho, Sumin Jung, Harim Hong, Kibeom Ban, Seonghoon Jung, Moon-Ryul Computer Vision and Pattern Recognition Machine Learning We introduce ConTEXTure, a generative network designed to create a texture map/atlas for a given 3D mesh using images from multiple viewpoints. The process begins with generating a front-view image from a text prompt, such as 'Napoleon, front view', describing the 3D mesh. Additional images from different viewpoints are derived from this front-view image and camera poses relative to it. ConTEXTure builds upon the TEXTure network, which uses text prompts for six viewpoints (e.g., 'Napoleon, front view', 'Napoleon, left view', etc.). However, TEXTure often generates images for non-front viewpoints that do not accurately represent those viewpoints.To address this issue, we employ Zero123++, which generates multiple view-consistent images for the six specified viewpoints simultaneously, conditioned on the initial front-view image and the depth maps of the mesh for the six viewpoints. By utilizing these view-consistent images, ConTEXTure learns the texture atlas from all viewpoint images concurrently, unlike previous methods that do so sequentially. This approach ensures that the rendered images from various viewpoints, including back, side, bottom, and top, are free from viewpoint irregularities. |
| title | ConTEXTure: Consistent Multiview Images to Texture |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2407.10558 |