Charles Bonnineau, W. Hamidouche, J. Travers, N. Sidaty, Jean-Yves Aubié, O. Déforges
{"title":"条件自编码器和学习空间可扩展性的超分辨率","authors":"Charles Bonnineau, W. Hamidouche, J. Travers, N. Sidaty, Jean-Yves Aubié, O. Déforges","doi":"10.1109/VCIP53242.2021.9675351","DOIUrl":null,"url":null,"abstract":"In this paper, we present CAESR, an hybrid learning-based coding approach for spatial scalability based on the versatile video coding (VVC) standard. Our framework considers a low-resolution signal encoded with VVC intra-mode as a base-layer (BL), and a deep conditional autoencoder with hyperprior (AE-HP) as an enhancement-layer (EL) model. The EL encoder takes as inputs both the upscaled BL reconstruction and the original image. Our approach relies on conditional coding that learns the optimal mixture of the source and the upscaled BL image, enabling better performance than residual coding. On the decoder side, a super-resolution (SR) module is used to recover high-resolution details and invert the conditional coding process. Experimental results have shown that our solution is competitive with the VVC full-resolution intra coding while being scalable.","PeriodicalId":114062,"journal":{"name":"2021 International Conference on Visual Communications and Image Processing (VCIP)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"CAESR: Conditional Autoencoder and Super-Resolution for Learned Spatial Scalability\",\"authors\":\"Charles Bonnineau, W. Hamidouche, J. Travers, N. Sidaty, Jean-Yves Aubié, O. Déforges\",\"doi\":\"10.1109/VCIP53242.2021.9675351\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, we present CAESR, an hybrid learning-based coding approach for spatial scalability based on the versatile video coding (VVC) standard. Our framework considers a low-resolution signal encoded with VVC intra-mode as a base-layer (BL), and a deep conditional autoencoder with hyperprior (AE-HP) as an enhancement-layer (EL) model. The EL encoder takes as inputs both the upscaled BL reconstruction and the original image. Our approach relies on conditional coding that learns the optimal mixture of the source and the upscaled BL image, enabling better performance than residual coding. On the decoder side, a super-resolution (SR) module is used to recover high-resolution details and invert the conditional coding process. Experimental results have shown that our solution is competitive with the VVC full-resolution intra coding while being scalable.\",\"PeriodicalId\":114062,\"journal\":{\"name\":\"2021 International Conference on Visual Communications and Image Processing (VCIP)\",\"volume\":\"38 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-12-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 International Conference on Visual Communications and Image Processing (VCIP)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/VCIP53242.2021.9675351\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 International Conference on Visual Communications and Image Processing (VCIP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/VCIP53242.2021.9675351","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
CAESR: Conditional Autoencoder and Super-Resolution for Learned Spatial Scalability
In this paper, we present CAESR, an hybrid learning-based coding approach for spatial scalability based on the versatile video coding (VVC) standard. Our framework considers a low-resolution signal encoded with VVC intra-mode as a base-layer (BL), and a deep conditional autoencoder with hyperprior (AE-HP) as an enhancement-layer (EL) model. The EL encoder takes as inputs both the upscaled BL reconstruction and the original image. Our approach relies on conditional coding that learns the optimal mixture of the source and the upscaled BL image, enabling better performance than residual coding. On the decoder side, a super-resolution (SR) module is used to recover high-resolution details and invert the conditional coding process. Experimental results have shown that our solution is competitive with the VVC full-resolution intra coding while being scalable.