Pub Date : 2023-11-30DOI: 10.1007/s41095-022-0305-5
Mingye Xu, Zhipeng Zhou, Yali Wang, Yu Qiao
Robustness and generalization are two challenging problems for learning point cloud representation. To tackle these problems, we first design a novel geometry coding model, which can effectively use an invariant eigengraph to group points with similar geometric information, even when such points are far from each other. We also introduce a large-scale point cloud dataset, PCNet184. It consists of 184 categories and 51,915 synthetic objects, which brings new challenges for point cloud classification, and provides a new benchmark to assess point cloud cross-domain generalization. Finally, we perform extensive experiments on point cloud classification, using ModelNet40, ScanObjectNN, and our PCNet184, and segmentation, using ShapeNetPart and S3DIS. Our method achieves comparable performance to state-of-the-art methods on these datasets, for both supervised and unsupervised learning. Code and our dataset are available at https://github.com/MingyeXu/PCNet184.
{"title":"Towards robustness and generalization of point cloud representation: A geometry coding method and a large-scale object-level dataset","authors":"Mingye Xu, Zhipeng Zhou, Yali Wang, Yu Qiao","doi":"10.1007/s41095-022-0305-5","DOIUrl":"https://doi.org/10.1007/s41095-022-0305-5","url":null,"abstract":"<p>Robustness and generalization are two challenging problems for learning point cloud representation. To tackle these problems, we first design a novel geometry coding model, which can effectively use an invariant eigengraph to group points with similar geometric information, even when such points are far from each other. We also introduce a large-scale point cloud dataset, PCNet184. It consists of 184 categories and 51,915 synthetic objects, which brings new challenges for point cloud classification, and provides a new benchmark to assess point cloud cross-domain generalization. Finally, we perform extensive experiments on point cloud classification, using ModelNet40, ScanObjectNN, and our PCNet184, and segmentation, using ShapeNetPart and S3DIS. Our method achieves comparable performance to state-of-the-art methods on these datasets, for both supervised and unsupervised learning. Code and our dataset are available at https://github.com/MingyeXu/PCNet184.\u0000</p>","PeriodicalId":37301,"journal":{"name":"Computational Visual Media","volume":null,"pages":null},"PeriodicalIF":6.9,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138494571","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-27DOI: 10.1007/s41095-022-0331-3
Huiyuan Tian, Li Zhang, Shijian Li, Min Yao, Gang Pan
{"title":"Pyramid-VAE-GAN: Transferring hierarchical latent variables for image inpainting","authors":"Huiyuan Tian, Li Zhang, Shijian Li, Min Yao, Gang Pan","doi":"10.1007/s41095-022-0331-3","DOIUrl":"https://doi.org/10.1007/s41095-022-0331-3","url":null,"abstract":"","PeriodicalId":37301,"journal":{"name":"Computational Visual Media","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44683429","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-03DOI: 10.1007/s41095-022-0297-1
W. Zhang, Wei Ke, D. Yang, Hao Sheng, Z. Xiong
{"title":"Light field super-resolution using complementary-view feature attention","authors":"W. Zhang, Wei Ke, D. Yang, Hao Sheng, Z. Xiong","doi":"10.1007/s41095-022-0297-1","DOIUrl":"https://doi.org/10.1007/s41095-022-0297-1","url":null,"abstract":"","PeriodicalId":37301,"journal":{"name":"Computational Visual Media","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42425698","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号