The paper, shared work between Tecnalia and the Computer Vision Center/Universitat Autònoma de Barcelona, makes use of synthetic blurring to show how we can use self-supervised and weakly supervised learning techniques to train a Convolutional Neural Net on the task of segmenting the defocus or motion-blurred areas of an image without having access to images annotated under real blur.
Next Wednesday, October 2nd, I’ll be giving an introductory talk to Deep Learning techniques at the Faculty of Science and Technology of the University of the Basque Country (UPV/EHU).