Zhihui He, Chengyuan Wang, Shidong Yang, Li Chen, Yanheng Zhou, Shuo Wang
{"title":"从解耦角度看可微分碰撞监督齿排列网络","authors":"Zhihui He, Chengyuan Wang, Shidong Yang, Li Chen, Yanheng Zhou, Shuo Wang","doi":"arxiv-2409.11937","DOIUrl":null,"url":null,"abstract":"Tooth arrangement is an essential step in the digital orthodontic planning\nprocess. Existing learning-based methods use hidden teeth features to directly\nregress teeth motions, which couples target pose perception and motion\nregression. It could lead to poor perceptions of three-dimensional\ntransformation. They also ignore the possible overlaps or gaps between teeth of\npredicted dentition, which is generally unacceptable. Therefore, we propose\nDTAN, a differentiable collision-supervised tooth arrangement network,\ndecoupling predicting tasks and feature modeling. DTAN decouples the tooth\narrangement task by first predicting the hidden features of the final teeth\nposes and then using them to assist in regressing the motions between the\nbeginning and target teeth. To learn the hidden features better, DTAN also\ndecouples the teeth-hidden features into geometric and positional features,\nwhich are further supervised by feature consistency constraints. Furthermore,\nwe propose a novel differentiable collision loss function for point cloud data\nto constrain the related gestures between teeth, which can be easily extended\nto other 3D point cloud tasks. We propose an arch-width guided tooth\narrangement network, named C-DTAN, to make the results controllable. We\nconstruct three different tooth arrangement datasets and achieve drastically\nimproved performance on accuracy and speed compared with existing methods.","PeriodicalId":501130,"journal":{"name":"arXiv - CS - Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Differentiable Collision-Supervised Tooth Arrangement Network with a Decoupling Perspective\",\"authors\":\"Zhihui He, Chengyuan Wang, Shidong Yang, Li Chen, Yanheng Zhou, Shuo Wang\",\"doi\":\"arxiv-2409.11937\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Tooth arrangement is an essential step in the digital orthodontic planning\\nprocess. Existing learning-based methods use hidden teeth features to directly\\nregress teeth motions, which couples target pose perception and motion\\nregression. It could lead to poor perceptions of three-dimensional\\ntransformation. They also ignore the possible overlaps or gaps between teeth of\\npredicted dentition, which is generally unacceptable. Therefore, we propose\\nDTAN, a differentiable collision-supervised tooth arrangement network,\\ndecoupling predicting tasks and feature modeling. DTAN decouples the tooth\\narrangement task by first predicting the hidden features of the final teeth\\nposes and then using them to assist in regressing the motions between the\\nbeginning and target teeth. To learn the hidden features better, DTAN also\\ndecouples the teeth-hidden features into geometric and positional features,\\nwhich are further supervised by feature consistency constraints. Furthermore,\\nwe propose a novel differentiable collision loss function for point cloud data\\nto constrain the related gestures between teeth, which can be easily extended\\nto other 3D point cloud tasks. We propose an arch-width guided tooth\\narrangement network, named C-DTAN, to make the results controllable. We\\nconstruct three different tooth arrangement datasets and achieve drastically\\nimproved performance on accuracy and speed compared with existing methods.\",\"PeriodicalId\":501130,\"journal\":{\"name\":\"arXiv - CS - Computer Vision and Pattern Recognition\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Computer Vision and Pattern Recognition\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.11937\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Computer Vision and Pattern Recognition","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.11937","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Differentiable Collision-Supervised Tooth Arrangement Network with a Decoupling Perspective
Tooth arrangement is an essential step in the digital orthodontic planning
process. Existing learning-based methods use hidden teeth features to directly
regress teeth motions, which couples target pose perception and motion
regression. It could lead to poor perceptions of three-dimensional
transformation. They also ignore the possible overlaps or gaps between teeth of
predicted dentition, which is generally unacceptable. Therefore, we propose
DTAN, a differentiable collision-supervised tooth arrangement network,
decoupling predicting tasks and feature modeling. DTAN decouples the tooth
arrangement task by first predicting the hidden features of the final teeth
poses and then using them to assist in regressing the motions between the
beginning and target teeth. To learn the hidden features better, DTAN also
decouples the teeth-hidden features into geometric and positional features,
which are further supervised by feature consistency constraints. Furthermore,
we propose a novel differentiable collision loss function for point cloud data
to constrain the related gestures between teeth, which can be easily extended
to other 3D point cloud tasks. We propose an arch-width guided tooth
arrangement network, named C-DTAN, to make the results controllable. We
construct three different tooth arrangement datasets and achieve drastically
improved performance on accuracy and speed compared with existing methods.