0569938 20230316110705.520230313235959.9 85134982515 000867754200066 10.1109/CVPR52688.2022.00074 10 s. P cav_un_epca*0570015978-1-6654-6946-31063-6919661-670PiscatawayIEEE2022 Deep learning architectures and techniques Image and video synthesis and generation Machine learning cav_un_auth*0447356 Wödlinger M. AT cav_un_auth*0293863 Kotera Jan UTIA-B Zpracování obrazové informace Department of Image Processing ZOI ZOI Department of Image Processing CZ Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0447357 Sablatnig R. AT http://library.utia.cas.cz/separaty/2023/ZOI/kotera-0569938.pdf We propose a learned method for stereo image compression that leverages the similarity of the left and right images in a stereo pair due to overlapping fields of view. The left image is compressed by a learned compression method based on an autoencoder with a hyperprior entropy model. The right image uses this information from the previously encoded left image in both the encoding and decoding stages. In particular, for the right image, we encode only the residual of its latent representation to the optimally shifted latent of the left image. On top of that, we also employ a stereo attention module to connect left and right images during decoding. The performance of the proposed method is evaluated on two benchmark stereo image datasets (Cityscapes and InStereo2K) and outperforms previous stereo image compression methods while being significantly smaller in model size. cav_un_auth*0447358 Conference on Computer Vision and Pattern Recognition 2022 (CVPR 2022) 20220619 20220624 New Orleans US JC 10000 10200 10201 2023 3 PR RVO:67985556 https://hdl.handle.net/11104/0341356 cav_un_auth*0301586 Technische Universität Wien TUW AT S n.a. Proceedings Paper Computer Science Artificial Intelligence|Imaging Science Photographic Technology 601 4.658 48.09 33.07 101222 Q1* 2022 85134982515 SCOPUS PUBMED 000867754200066 WOS cav_un_epca*0570015 2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022) IEEE 2022 Piscataway 661 670 978-1-6654-6946-3 IEEE Conference on Computer Vision and Pattern Recognition 1063-6919