In 10/2021-12/2022 postdoc in Technische Universität Wien (TUW), Computer Vision Lab (CVL) with Prof. Robert Sablatnig, working on EU H2020 project "AI Stream" (learned image compression).
The project focuses on the protection of video and image content and looks at ways to prevent illegal sharing. It will explore how artificial intelligence methods can circumvent these protections and the challenges of applying protection to large volumes of data.
Digital image acquisition is often accompanied with its degradation by blur (out-of-focus, motion etc.) and noise. In many cases, the degradation process can be modeled by convolution g=u*h+n where g denotes the acquired image, u the original image, h the convolution mask (blur), and n random noise. The goal of deconvolution is to recover the original image based on the observed image.