Saved in:
Bibliographic Details
Main Authors: Xu, Chenfan, Liu, Zhentao, Liu, Yuan, Dou, Yulong, Wu, Jiamin, Wang, Jiepeng, Wang, Minjiao, Shen, Dinggang, Cui, Zhiming
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