{"title":"基于深度图同质性的3D-HEVC互编码有效CU大小决策算法","authors":"Siham Bakkouri, A. Elyousfi","doi":"10.1109/ISCV49265.2020.9204037","DOIUrl":null,"url":null,"abstract":"High efficiency video coding standard-based 3D video (3D-HEVC) is an extension of high efficiency video coding standard (HEVC) to improve the efficiency of the multiview video plus depth (MVD). In 3D-HEVC inter-coding, The quad-tree structure of coding unit (CU) partition supports different sizes from 64×64 to 8×8, namely, CU sizes. The CU partitioning process achieves the highest coding efficiency, but it brings an extremely large encoding time and a large computational complexity occurs which limits the 3D-HEVC encoder from practical applications. In this paper, an early termination of CU size is proposed for dependent views in 3D-HEVC depth map encoding. The proposed algorithm based on homogeneity classification of a depth map CU using an unsupervised classification algorithm. Based on the classification results, the proposed method determines whether a depth CU must be or not be split into smaller sizes. Experimental results show that the proposed approach can achieve a reduction of computational complexity for depth map encoding with a negligible reduction of coding performance.","PeriodicalId":313743,"journal":{"name":"2020 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"Effective CU size decision algorithm based on depth map homogeneity for 3D-HEVC inter-coding\",\"authors\":\"Siham Bakkouri, A. Elyousfi\",\"doi\":\"10.1109/ISCV49265.2020.9204037\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"High efficiency video coding standard-based 3D video (3D-HEVC) is an extension of high efficiency video coding standard (HEVC) to improve the efficiency of the multiview video plus depth (MVD). In 3D-HEVC inter-coding, The quad-tree structure of coding unit (CU) partition supports different sizes from 64×64 to 8×8, namely, CU sizes. The CU partitioning process achieves the highest coding efficiency, but it brings an extremely large encoding time and a large computational complexity occurs which limits the 3D-HEVC encoder from practical applications. In this paper, an early termination of CU size is proposed for dependent views in 3D-HEVC depth map encoding. The proposed algorithm based on homogeneity classification of a depth map CU using an unsupervised classification algorithm. Based on the classification results, the proposed method determines whether a depth CU must be or not be split into smaller sizes. Experimental results show that the proposed approach can achieve a reduction of computational complexity for depth map encoding with a negligible reduction of coding performance.\",\"PeriodicalId\":313743,\"journal\":{\"name\":\"2020 International Conference on Intelligent Systems and Computer Vision (ISCV)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-06-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 International Conference on Intelligent Systems and Computer Vision (ISCV)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ISCV49265.2020.9204037\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 International Conference on Intelligent Systems and Computer Vision (ISCV)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISCV49265.2020.9204037","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Effective CU size decision algorithm based on depth map homogeneity for 3D-HEVC inter-coding
High efficiency video coding standard-based 3D video (3D-HEVC) is an extension of high efficiency video coding standard (HEVC) to improve the efficiency of the multiview video plus depth (MVD). In 3D-HEVC inter-coding, The quad-tree structure of coding unit (CU) partition supports different sizes from 64×64 to 8×8, namely, CU sizes. The CU partitioning process achieves the highest coding efficiency, but it brings an extremely large encoding time and a large computational complexity occurs which limits the 3D-HEVC encoder from practical applications. In this paper, an early termination of CU size is proposed for dependent views in 3D-HEVC depth map encoding. The proposed algorithm based on homogeneity classification of a depth map CU using an unsupervised classification algorithm. Based on the classification results, the proposed method determines whether a depth CU must be or not be split into smaller sizes. Experimental results show that the proposed approach can achieve a reduction of computational complexity for depth map encoding with a negligible reduction of coding performance.