Nadcházející semináře

  • Filip Sroubek (UTIA): Inverse problems in image restoration: from basic principles to current deep-learning trends

    17.12.2018 14:00 @ Hora Informaticae

    We rely on images with ever growing emphasis. Our perception of the world is however limited by imperfect measuring conditions and acquisition devices. By image restoration, we mean mathematical methods for removing degradation from images. Two prominent topics of image restoration, which has evolved considerably in the last 10 years, are blind deconvolution and superresolution. Deconvolution by itself is an ill-posed inverse problem due to the nature of the blur kernel. The blind case, when the blur kernel is unknown, is even more challenging and requires special optimization approaches to converge to the correct solution. Superresolution extends blind deconvolution by also recovering the lost spatial resolution of images. The talk will cover recent advances in both topics. Various real acquisition scenarios will be discussed together with proposed solutions using either state-of-the-art proximal algorithms or convolutional neural networks. Interesting new applications of video analysis will conclude the talk.