2 papers
cs.CV2016
Compression Artifacts Removal Using Convolutional Neural Networks
Pavel Svoboda, Michal Hradis, David Barina +1
This paper shows that it is possible to train large and deep convolutional neural networks (CNN) for JPEG compression artifacts reduction, and that such networks can provide signif…
cs.CV2016
CNN for License Plate Motion Deblurring
Pavel Svoboda, Michal Hradis, Lukas Marsik +1
In this work we explore the previously proposed approach of direct blind deconvolution and denoising with convolutional neural networks in a situation where the blur kernels are pa…