Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2412.03225 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912501711503360 |
|---|---|
| author | Ma, Xiaohe Deschaintre, Valentin Hašan, Miloš Luan, Fujun Zhou, Kun Wu, Hongzhi Hu, Yiwei |
| author_facet | Ma, Xiaohe Deschaintre, Valentin Hašan, Miloš Luan, Fujun Zhou, Kun Wu, Hongzhi Hu, Yiwei |
| contents | High-quality material generation is key for virtual environment authoring and inverse rendering. We propose MaterialPicker, a multi-modal material generator leveraging a Diffusion Transformer (DiT) architecture, improving and simplifying the creation of high-quality materials from text prompts and/or photographs. Our method can generate a material based on an image crop of a material sample, even if the captured surface is distorted, viewed at an angle or partially occluded, as is often the case in photographs of natural scenes. We further allow the user to specify a text prompt to provide additional guidance for the generation. We finetune a pre-trained DiT-based video generator into a material generator, where each material map is treated as a frame in a video sequence. We evaluate our approach both quantitatively and qualitatively and show that it enables more diverse material generation and better distortion correction than previous work. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_03225 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MaterialPicker: Multi-Modal DiT-Based Material Generation Ma, Xiaohe Deschaintre, Valentin Hašan, Miloš Luan, Fujun Zhou, Kun Wu, Hongzhi Hu, Yiwei Computer Vision and Pattern Recognition High-quality material generation is key for virtual environment authoring and inverse rendering. We propose MaterialPicker, a multi-modal material generator leveraging a Diffusion Transformer (DiT) architecture, improving and simplifying the creation of high-quality materials from text prompts and/or photographs. Our method can generate a material based on an image crop of a material sample, even if the captured surface is distorted, viewed at an angle or partially occluded, as is often the case in photographs of natural scenes. We further allow the user to specify a text prompt to provide additional guidance for the generation. We finetune a pre-trained DiT-based video generator into a material generator, where each material map is treated as a frame in a video sequence. We evaluate our approach both quantitatively and qualitatively and show that it enables more diverse material generation and better distortion correction than previous work. |
| title | MaterialPicker: Multi-Modal DiT-Based Material Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.03225 |