Pub Date : 2024-09-16DOI: 10.1109/TBC.2024.3453631
{"title":"IEEE Transactions on Broadcasting Information for Authors","authors":"","doi":"10.1109/TBC.2024.3453631","DOIUrl":"https://doi.org/10.1109/TBC.2024.3453631","url":null,"abstract":"","PeriodicalId":13159,"journal":{"name":"IEEE Transactions on Broadcasting","volume":"70 3","pages":"C3-C4"},"PeriodicalIF":3.2,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10680489","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142235706","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-16DOI: 10.1109/TBC.2024.3453611
{"title":"IEEE Transactions on Broadcasting Information for Authors","authors":"","doi":"10.1109/TBC.2024.3453611","DOIUrl":"https://doi.org/10.1109/TBC.2024.3453611","url":null,"abstract":"","PeriodicalId":13159,"journal":{"name":"IEEE Transactions on Broadcasting","volume":"70 3","pages":"C3-C4"},"PeriodicalIF":3.2,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10680491","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142235712","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Learning-based point cloud compression has achieved great success in Rate-Distortion (RD) efficiency. Existing methods usually utilize Variational AutoEncoder (VAE) network, which might lead to poor detail reconstruction and high computational complexity. To address these issues, we propose a Scale-adaptive Asymmetric Sparse Variational AutoEncoder (SAS-VAE) in this work. First, we develop an Asymmetric Multiscale Sparse Convolution (AMSC), which exploits multi-resolution branches to aggregate multiscale features at encoder, and excludes symmetric feature fusion branches to control the model complexity at decoder. Second, we design a Scale Adaptive Feature Refinement Structure (SAFRS) to adaptively adjust the number of Feature Refinement Modules (FRMs), thereby improving RD performance with an acceptable computational overhead. Third, we implement our framework with AMSC and SAFRS, and train it with an RD loss based on Fine-grained Weighted Binary Cross-Entropy (FWBCE) function. Experimental results on 8iVFB, Owlii, and MVUV datasets show that our method outperforms several popular methods, with a 90.0% time reduction and a 51.8% BD-BR saving compared with V-PCC. The code will be available soon at https://github.com/fancj2017/SAS-VAE .
{"title":"Scale-Adaptive Asymmetric Sparse Variational AutoEncoder for Point Cloud Compression","authors":"Jian Chen;Yingtao Zhu;Wei Huang;Chengdong Lan;Tiesong Zhao","doi":"10.1109/TBC.2024.3437161","DOIUrl":"10.1109/TBC.2024.3437161","url":null,"abstract":"Learning-based point cloud compression has achieved great success in Rate-Distortion (RD) efficiency. Existing methods usually utilize Variational AutoEncoder (VAE) network, which might lead to poor detail reconstruction and high computational complexity. To address these issues, we propose a Scale-adaptive Asymmetric Sparse Variational AutoEncoder (SAS-VAE) in this work. First, we develop an Asymmetric Multiscale Sparse Convolution (AMSC), which exploits multi-resolution branches to aggregate multiscale features at encoder, and excludes symmetric feature fusion branches to control the model complexity at decoder. Second, we design a Scale Adaptive Feature Refinement Structure (SAFRS) to adaptively adjust the number of Feature Refinement Modules (FRMs), thereby improving RD performance with an acceptable computational overhead. Third, we implement our framework with AMSC and SAFRS, and train it with an RD loss based on Fine-grained Weighted Binary Cross-Entropy (FWBCE) function. Experimental results on 8iVFB, Owlii, and MVUV datasets show that our method outperforms several popular methods, with a 90.0% time reduction and a 51.8% BD-BR saving compared with V-PCC. The code will be available soon at \u0000<uri>https://github.com/fancj2017/SAS-VAE</uri>\u0000.","PeriodicalId":13159,"journal":{"name":"IEEE Transactions on Broadcasting","volume":"70 3","pages":"884-894"},"PeriodicalIF":3.2,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142207649","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Retouched Face Image Quality Assessment Based on Differential Perception and Textual Prompt","authors":"Tianwei Zhou, Songbai Tan, Gang Li, Shishun Tian, Chang Tang, Zhihua Wang, Guanghui Yue","doi":"10.1109/tbc.2024.3447454","DOIUrl":"https://doi.org/10.1109/tbc.2024.3447454","url":null,"abstract":"","PeriodicalId":13159,"journal":{"name":"IEEE Transactions on Broadcasting","volume":"31 1","pages":""},"PeriodicalIF":4.5,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142207650","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：