Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2407.11419 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916326091522048 |
|---|---|
| author | Xu, Chenfan Liu, Zhentao Liu, Yuan Dou, Yulong Wu, Jiamin Wang, Jiepeng Wang, Minjiao Shen, Dinggang Cui, Zhiming |
| author_facet | Xu, Chenfan Liu, Zhentao Liu, Yuan Dou, Yulong Wu, Jiamin Wang, Jiepeng Wang, Minjiao Shen, Dinggang Cui, Zhiming |
| contents | Orthodontic treatment usually requires regular face-to-face examinations to monitor dental conditions of the patients. When in-person diagnosis is not feasible, an alternative is to utilize five intra-oral photographs for remote dental monitoring. However, it lacks of 3D information, and how to reconstruct 3D dental models from such sparse view photographs is a challenging problem. In this study, we propose a 3D teeth reconstruction framework, named TeethDreamer, aiming to restore the shape and position of the upper and lower teeth. Given five intra-oral photographs, our approach first leverages a large diffusion model's prior knowledge to generate novel multi-view images with known poses to address sparse inputs and then reconstructs high-quality 3D teeth models by neural surface reconstruction. To ensure the 3D consistency across generated views, we integrate a 3D-aware feature attention mechanism in the reverse diffusion process. Moreover, a geometry-aware normal loss is incorporated into the teeth reconstruction process to enhance geometry accuracy. Extensive experiments demonstrate the superiority of our method over current state-of-the-arts, giving the potential to monitor orthodontic treatment remotely. Our code is available at https://github.com/ShanghaiTech-IMPACT/TeethDreamer |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_11419 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TeethDreamer: 3D Teeth Reconstruction from Five Intra-oral Photographs Xu, Chenfan Liu, Zhentao Liu, Yuan Dou, Yulong Wu, Jiamin Wang, Jiepeng Wang, Minjiao Shen, Dinggang Cui, Zhiming Computer Vision and Pattern Recognition Orthodontic treatment usually requires regular face-to-face examinations to monitor dental conditions of the patients. When in-person diagnosis is not feasible, an alternative is to utilize five intra-oral photographs for remote dental monitoring. However, it lacks of 3D information, and how to reconstruct 3D dental models from such sparse view photographs is a challenging problem. In this study, we propose a 3D teeth reconstruction framework, named TeethDreamer, aiming to restore the shape and position of the upper and lower teeth. Given five intra-oral photographs, our approach first leverages a large diffusion model's prior knowledge to generate novel multi-view images with known poses to address sparse inputs and then reconstructs high-quality 3D teeth models by neural surface reconstruction. To ensure the 3D consistency across generated views, we integrate a 3D-aware feature attention mechanism in the reverse diffusion process. Moreover, a geometry-aware normal loss is incorporated into the teeth reconstruction process to enhance geometry accuracy. Extensive experiments demonstrate the superiority of our method over current state-of-the-arts, giving the potential to monitor orthodontic treatment remotely. Our code is available at https://github.com/ShanghaiTech-IMPACT/TeethDreamer |
| title | TeethDreamer: 3D Teeth Reconstruction from Five Intra-oral Photographs |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.11419 |