Organization contact [name= K. Desnos (kdesnos at insa-rennes.fr)] Mailing list: You can subscribe to a dedicated mailing-list, that will exclusively be used to send seminar and Ph.D. defense announcements. To subscribe, send an e-mail to sympa@insa-rennes.fr with the following subject line (with YOUR first and last names): subscribe vaader-seminars FirstName LastName Next Seminars 01.12.2022 - 10:15 INSA Build. 10, Room 229 & Zoom
11/25/2022by Marwa Tarchouli (IETR VAADER) - 2022.11.22 Video {%youtube g2F8pm5wpOg%} Abstract End-to-end learned image and video codecs, based on auto-encoder architecture, adapt naturally to image resolution, thanks to their convolutional aspect. However, while coding high resolution images, these codecs face hardware problems such as memory saturation. Patch-based image coding with learned image codecs solve these problems. Nevertheless, this method creates block artifacts in the reconstructed image which highly deteriorates its quality. This paper proposes a patch-based image coding solution, which is based on an end-to-end learned model, and which remedies the block artifacts. It consists in coding overlapping patches of the image and reconstruct them into a decoded image using a weighting function. This approach manages to slightly outperform the performance of full résolution image coding with an end-to-end learned model while being adaptable to different memory size.
11/25/2022by Beuve Nicolas (IETR VAADER) - 2023.01.10 Abstract
11/16/2022by Vozel Benoit (IETR - MULTIP) - 2022.11.10 Video {%youtube HRfsNOVGWX4%} Abstract Work by Vladimir Lukin, Bogdan Kovalenko, Sergii Kryvenko, Victoriya Naumenko and Benoit Vozel We investigate lossy compression of noisy images. In this case, there are some peculiarities relating to noise filtering effect and analysis of compression technique performance. As a result of noise filtering due to lossy compression, the so-called optimal operation point (OOP) may exist. OOP is related to such parameters of a coder that quality of a compressed image is closer to the corresponding noise-free (true) image compared to quality of uncompressed (original, noisy) image where quality is characterized by a certain metric, conventional (PSNR) or visual one (PSNR-HVS-M, PSNR-HA, MDSI). If OOP for a given noisy image exists, it occurs expedient to automatically compress an image under interest in OOP or, at least, its neighbourhood. We show that it is, in general, possible to predict OOP existence (according to different metrics) before image compression. It is also possible to reasonably set the coder parameters where better portable graphics (BPG) coder is paid here the main attention. The extensions of the proposed approach to joint compression of three-component images are discussed. Image subsampling in color components is studied. The possibility of OOP existence for visual quality metrics PSNR-HA and MDSI is illustrated.
11/15/2022