RGB oralscan video-based orthodontic treatment monitoring  

作　　者：Yan TIAN Hanshi FU Hao WANG Yuqi LIU Zhaocheng XU Hong CHEN Jianyuan LI Ruili WANG 

机构地区：[1]School of Computer Science and Technology,Zhejiang Gongshang University,Hangzhou 310018,China [2]Shining3D Tech Co.,Ltd.,Hangzhou 311258,China [3]School of Information and Technology,Monash University,Melbourne 3800,Australia [4]School of Mathematical and Computational Sciences,Massey University,Auckland 0632,New Zealand [5]Department of Stomatology,Zhejiang Provincial People’s Hospital,Hangzhou Medical College,Hangzhou 310014,China [6]School of Computer and Computing Science,Zhejiang University City College,Hangzhou 310015,China

出　　处：《Science China(Information Sciences)》2024年第1期120-135,共16页中国科学（信息科学）（英文版）

基　　金：supported in part by National Natural Science Foundation of China(Grant Nos.61972351,62111530300);Zhejiang Province R&D Key Project(other categories)(Grant No.2022C03149);Special Project for Basic Business Expenses of Zhejiang Provincial Colleges and Universities(Grant No.JRK22003);Opening Foundation of State Key Laboratory of Virtual Reality Technology and System of Beihang University(Grant No.VRLAB2023B02)。

摘　　要：Orthodontic treatment monitoring involves using current images and previous 3D models to estimate the relative position of individual teeth before and after orthodontic treatment.This process differs from image-based object 6D pose estimation due to the gingiva deformation and varying pose offsets for each tooth during treatment.Motivated by the fact that the poses of molars remain relatively fixed in implicit orthodontics,we design an approach that employs multiview pose evaluation and bidirectional temporal propagation for jaw pose estimation and then employs an iteration-based method for tooth alignment.To handle changes in tooth appearance or location with weak texture across frames,we also introduce an instance propagation module that leverages positional and semantic information to explore instance relations in the temporal domain.We evaluated the performance of our approach using both the Shining3D tooth pose dataset and the Aoralscan3 tooth registration dataset.Our experimental results demonstrate remarkable accuracy improvements compared with existing methods.

关 键 词：s digital dentistry object 6D pose estimation deep learning computer vision 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] R783.5[自动化与计算机技术—计算机科学与技术]