2016/02/25 by Pavel Svoboda, Svoboda, Pavel, Michal Hradiš +5 · 2 citations
Computer Science · #Advanced Image Processing Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image and Object Detection Techniques #Image and Signal Denoising Methods
paper · pdf · doi:10.48550/arxiv.1602.07873
openalex publication_date 2016/02/25 · openalex created_date 2017/08/31 · openalex updated_date 2026/07/28
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 partially constrained. We focus on blurred images from a real-life traffic surveillance system, on which we, for the first time, demonstrate that neural networks trained on artificial data provide superior reconstruction quality on real images compared to traditional blind deconvolution methods. The training data is easy to obtain by blurring sharp photos from a target system with a very rough approximation of the expected blur kernels, thereby allowing custom CNNs to be trained for a specific application (image content and blur range). Additionally, we evaluate the behavior and limits of the CNNs with respect to blur direction range and length.