Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2409.19989 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929521754636288 |
|---|---|
| author | Kim, Jangyeong Kang, Donggoo Choi, Junyoung Wi, Jeonga Gwon, Junho Bae, Jiun Yoon, Dumim Han, Junghyun |
| author_facet | Kim, Jangyeong Kang, Donggoo Choi, Junyoung Wi, Jeonga Gwon, Junho Bae, Jiun Yoon, Dumim Han, Junghyun |
| contents | Text-to-texture generation has recently attracted increasing attention, but existing methods often suffer from the problems of view inconsistencies, apparent seams, and misalignment between textures and the underlying mesh. In this paper, we propose a robust text-to-texture method for generating consistent and seamless textures that are well aligned with the mesh. Our method leverages state-of-the-art 2D diffusion models, including SDXL and multiple ControlNets, to capture structural features and intricate details in the generated textures. The method also employs a symmetrical view synthesis strategy combined with regional prompts for enhancing view consistency. Additionally, it introduces novel texture blending and soft-inpainting techniques, which significantly reduce the seam regions. Extensive experiments demonstrate that our method outperforms existing state-of-the-art methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_19989 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RoCoTex: A Robust Method for Consistent Texture Synthesis with Diffusion Models Kim, Jangyeong Kang, Donggoo Choi, Junyoung Wi, Jeonga Gwon, Junho Bae, Jiun Yoon, Dumim Han, Junghyun Computer Vision and Pattern Recognition Graphics Text-to-texture generation has recently attracted increasing attention, but existing methods often suffer from the problems of view inconsistencies, apparent seams, and misalignment between textures and the underlying mesh. In this paper, we propose a robust text-to-texture method for generating consistent and seamless textures that are well aligned with the mesh. Our method leverages state-of-the-art 2D diffusion models, including SDXL and multiple ControlNets, to capture structural features and intricate details in the generated textures. The method also employs a symmetrical view synthesis strategy combined with regional prompts for enhancing view consistency. Additionally, it introduces novel texture blending and soft-inpainting techniques, which significantly reduce the seam regions. Extensive experiments demonstrate that our method outperforms existing state-of-the-art methods. |
| title | RoCoTex: A Robust Method for Consistent Texture Synthesis with Diffusion Models |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2409.19989 |