{"title":"用于三维形状匹配和检索的深度学习形状描述符","authors":"J. Xie, Yi Fang, Fan Zhu, E. Wong","doi":"10.1109/CVPR.2015.7298732","DOIUrl":null,"url":null,"abstract":"Complex geometric structural variations of 3D model usually pose great challenges in 3D shape matching and retrieval. In this paper, we propose a high-level shape feature learning scheme to extract features that are insensitive to deformations via a novel discriminative deep auto-encoder. First, a multiscale shape distribution is developed for use as input to the auto-encoder. Then, by imposing the Fisher discrimination criterion on the neurons in the hidden layer, we developed a novel discriminative deep auto-encoder for shape feature learning. Finally, the neurons in the hidden layers from multiple discriminative auto-encoders are concatenated to form a shape descriptor for 3D shape matching and retrieval. The proposed method is evaluated on the representative datasets that contain 3D models with large geometric variations, i.e., Mcgill and SHREC'10 ShapeGoogle datasets. Experimental results on the benchmark datasets demonstrate the effectiveness of the proposed method for 3D shape matching and retrieval.","PeriodicalId":444472,"journal":{"name":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"114 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"134","resultStr":"{\"title\":\"Deepshape: Deep learned shape descriptor for 3D shape matching and retrieval\",\"authors\":\"J. Xie, Yi Fang, Fan Zhu, E. Wong\",\"doi\":\"10.1109/CVPR.2015.7298732\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Complex geometric structural variations of 3D model usually pose great challenges in 3D shape matching and retrieval. In this paper, we propose a high-level shape feature learning scheme to extract features that are insensitive to deformations via a novel discriminative deep auto-encoder. First, a multiscale shape distribution is developed for use as input to the auto-encoder. Then, by imposing the Fisher discrimination criterion on the neurons in the hidden layer, we developed a novel discriminative deep auto-encoder for shape feature learning. Finally, the neurons in the hidden layers from multiple discriminative auto-encoders are concatenated to form a shape descriptor for 3D shape matching and retrieval. The proposed method is evaluated on the representative datasets that contain 3D models with large geometric variations, i.e., Mcgill and SHREC'10 ShapeGoogle datasets. Experimental results on the benchmark datasets demonstrate the effectiveness of the proposed method for 3D shape matching and retrieval.\",\"PeriodicalId\":444472,\"journal\":{\"name\":\"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)\",\"volume\":\"114 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2015-06-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"134\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CVPR.2015.7298732\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CVPR.2015.7298732","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Deepshape: Deep learned shape descriptor for 3D shape matching and retrieval
Complex geometric structural variations of 3D model usually pose great challenges in 3D shape matching and retrieval. In this paper, we propose a high-level shape feature learning scheme to extract features that are insensitive to deformations via a novel discriminative deep auto-encoder. First, a multiscale shape distribution is developed for use as input to the auto-encoder. Then, by imposing the Fisher discrimination criterion on the neurons in the hidden layer, we developed a novel discriminative deep auto-encoder for shape feature learning. Finally, the neurons in the hidden layers from multiple discriminative auto-encoders are concatenated to form a shape descriptor for 3D shape matching and retrieval. The proposed method is evaluated on the representative datasets that contain 3D models with large geometric variations, i.e., Mcgill and SHREC'10 ShapeGoogle datasets. Experimental results on the benchmark datasets demonstrate the effectiveness of the proposed method for 3D shape matching and retrieval.