Blind Deblurring using Deep Learning: A Survey

View

• Paper

Abstract

We inspect various deep learning based solutions and provide holistic understanding of various architectures that have evolved over the past few years to solve blind deblurring. The introductory work used deep learning to estimate some features of the blur kernel and then moved onto predicting the blur kernel entirely, which converts the problem into non-blind deblurring. The recent state of the art techniques are end to end i.e they dont estimate the blur kernel rather try to estimate the latent sharp image directly from the blurred image. The benchmarking PSNR and SSIM values on standard datasets of GOPRO and K¨ohler using various architectures are also provided

Citation

S. Sahu, M. Lenka, and P. Sa, Blind deblurring using deep learning: A survey, 2019. arXiv: 1907.10128

@@misc{sahu2019blind,
      title={Blind Deblurring using Deep Learning: A Survey}, 
      author={Sahu, Siddhant and Lenka, Manoj and Sa, Pankaj},
      year={2019},
      eprint={1907.10128},
      archivePrefix={arXiv}
}