{"title":"基于学习的移动AR大物体局部观测六自由度相机姿态估计*","authors":"Jean-Pierre Lomaliza, Hanhoon Park","doi":"10.1145/3359996.3364718","DOIUrl":null,"url":null,"abstract":"We propose a method that estimates 6-DoF camera pose from a partially visible large object, by exploiting information of its subparts that are detected using a state-of-the-art convolutional neural network (CNN). The trained CNN outputs two-dimensional bounding boxes around subparts and associated classes. Information from detection is then fed to a deep neural network that regresses to camera's 6-DoF poses. Experimental results show that the proposed method is more robust to occlusions than conventional learning-based methods.","PeriodicalId":393864,"journal":{"name":"Proceedings of the 25th ACM Symposium on Virtual Reality Software and Technology","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2019-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Learning-based Estimation of 6-DoF Camera Poses from Partial Observation of Large Objects for Mobile AR*\",\"authors\":\"Jean-Pierre Lomaliza, Hanhoon Park\",\"doi\":\"10.1145/3359996.3364718\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We propose a method that estimates 6-DoF camera pose from a partially visible large object, by exploiting information of its subparts that are detected using a state-of-the-art convolutional neural network (CNN). The trained CNN outputs two-dimensional bounding boxes around subparts and associated classes. Information from detection is then fed to a deep neural network that regresses to camera's 6-DoF poses. Experimental results show that the proposed method is more robust to occlusions than conventional learning-based methods.\",\"PeriodicalId\":393864,\"journal\":{\"name\":\"Proceedings of the 25th ACM Symposium on Virtual Reality Software and Technology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-11-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 25th ACM Symposium on Virtual Reality Software and Technology\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3359996.3364718\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 25th ACM Symposium on Virtual Reality Software and Technology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3359996.3364718","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Learning-based Estimation of 6-DoF Camera Poses from Partial Observation of Large Objects for Mobile AR*
We propose a method that estimates 6-DoF camera pose from a partially visible large object, by exploiting information of its subparts that are detected using a state-of-the-art convolutional neural network (CNN). The trained CNN outputs two-dimensional bounding boxes around subparts and associated classes. Information from detection is then fed to a deep neural network that regresses to camera's 6-DoF poses. Experimental results show that the proposed method is more robust to occlusions than conventional learning-based methods.