Deblurring Photographs of Characters Using Deep Neural Networks
This work addresses a specific challenge in image processing for character deblurring, but it is incremental as it applies existing techniques to a new dataset.
The paper tackles the problem of deblurring character images without known point spread functions, using a method that estimates transformations and PSFs to train a deep neural network, achieving successful reconstruction on the first 10 stages of the HDC2021 dataset.
In this paper, we present our approach for the Helsinki Deblur Challenge (HDC2021). The task of this challenge is to deblur images of characters without knowing the point spread function (PSF). The organizers provided a dataset of pairs of sharp and blurred images. Our method consists of three steps: First, we estimate a warping transformation of the images to align the sharp images with the blurred ones. Next, we estimate the PSF using a quasi-Newton method. The estimated PSF allows to generate additional pairs of sharp and blurred images. Finally, we train a deep convolutional neural network to reconstruct the sharp images from the blurred images. Our method is able to successfully reconstruct images from the first 10 stages of the HDC 2021 data. Our code is available at https://github.com/hhu-machine-learning/hdc2021-psfnn.