{"title":"LFIC-DRASC:利用分离表示和非对称条带卷积进行深度光场图像压缩","authors":"Shiyu Feng, Yun Zhang, Linwei Zhu, Sam Kwong","doi":"arxiv-2409.11711","DOIUrl":null,"url":null,"abstract":"Light-Field (LF) image is emerging 4D data of light rays that is capable of\nrealistically presenting spatial and angular information of 3D scene. However,\nthe large data volume of LF images becomes the most challenging issue in\nreal-time processing, transmission, and storage. In this paper, we propose an\nend-to-end deep LF Image Compression method Using Disentangled Representation\nand Asymmetrical Strip Convolution (LFIC-DRASC) to improve coding efficiency.\nFirstly, we formulate the LF image compression problem as learning a\ndisentangled LF representation network and an image encoding-decoding network.\nSecondly, we propose two novel feature extractors that leverage the structural\nprior of LF data by integrating features across different dimensions.\nMeanwhile, disentangled LF representation network is proposed to enhance the LF\nfeature disentangling and decoupling. Thirdly, we propose the LFIC-DRASC for LF\nimage compression, where two Asymmetrical Strip Convolution (ASC) operators,\ni.e. horizontal and vertical, are proposed to capture long-range correlation in\nLF feature space. These two ASC operators can be combined with the square\nconvolution to further decouple LF features, which enhances the model ability\nin representing intricate spatial relationships. Experimental results\ndemonstrate that the proposed LFIC-DRASC achieves an average of 20.5\\% bit rate\nreductions comparing with the state-of-the-art methods.","PeriodicalId":501289,"journal":{"name":"arXiv - EE - Image and Video Processing","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"LFIC-DRASC: Deep Light Field Image Compression Using Disentangled Representation and Asymmetrical Strip Convolution\",\"authors\":\"Shiyu Feng, Yun Zhang, Linwei Zhu, Sam Kwong\",\"doi\":\"arxiv-2409.11711\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Light-Field (LF) image is emerging 4D data of light rays that is capable of\\nrealistically presenting spatial and angular information of 3D scene. However,\\nthe large data volume of LF images becomes the most challenging issue in\\nreal-time processing, transmission, and storage. In this paper, we propose an\\nend-to-end deep LF Image Compression method Using Disentangled Representation\\nand Asymmetrical Strip Convolution (LFIC-DRASC) to improve coding efficiency.\\nFirstly, we formulate the LF image compression problem as learning a\\ndisentangled LF representation network and an image encoding-decoding network.\\nSecondly, we propose two novel feature extractors that leverage the structural\\nprior of LF data by integrating features across different dimensions.\\nMeanwhile, disentangled LF representation network is proposed to enhance the LF\\nfeature disentangling and decoupling. Thirdly, we propose the LFIC-DRASC for LF\\nimage compression, where two Asymmetrical Strip Convolution (ASC) operators,\\ni.e. horizontal and vertical, are proposed to capture long-range correlation in\\nLF feature space. These two ASC operators can be combined with the square\\nconvolution to further decouple LF features, which enhances the model ability\\nin representing intricate spatial relationships. Experimental results\\ndemonstrate that the proposed LFIC-DRASC achieves an average of 20.5\\\\% bit rate\\nreductions comparing with the state-of-the-art methods.\",\"PeriodicalId\":501289,\"journal\":{\"name\":\"arXiv - EE - Image and Video Processing\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - EE - Image and Video Processing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.11711\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - EE - Image and Video Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.11711","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
LFIC-DRASC: Deep Light Field Image Compression Using Disentangled Representation and Asymmetrical Strip Convolution
Light-Field (LF) image is emerging 4D data of light rays that is capable of
realistically presenting spatial and angular information of 3D scene. However,
the large data volume of LF images becomes the most challenging issue in
real-time processing, transmission, and storage. In this paper, we propose an
end-to-end deep LF Image Compression method Using Disentangled Representation
and Asymmetrical Strip Convolution (LFIC-DRASC) to improve coding efficiency.
Firstly, we formulate the LF image compression problem as learning a
disentangled LF representation network and an image encoding-decoding network.
Secondly, we propose two novel feature extractors that leverage the structural
prior of LF data by integrating features across different dimensions.
Meanwhile, disentangled LF representation network is proposed to enhance the LF
feature disentangling and decoupling. Thirdly, we propose the LFIC-DRASC for LF
image compression, where two Asymmetrical Strip Convolution (ASC) operators,
i.e. horizontal and vertical, are proposed to capture long-range correlation in
LF feature space. These two ASC operators can be combined with the square
convolution to further decouple LF features, which enhances the model ability
in representing intricate spatial relationships. Experimental results
demonstrate that the proposed LFIC-DRASC achieves an average of 20.5\% bit rate
reductions comparing with the state-of-the-art methods.