IVCVJul 23, 2019

Blind Deblurring using Deep Learning: A Survey

arXiv:1907.10128v121 citations
Originality Synthesis-oriented
AI Analysis

It provides a comprehensive overview for researchers and practitioners in computer vision, but is incremental as it synthesizes existing work without introducing new methods.

This survey examines deep learning approaches for blind deblurring, tracing the evolution from methods that estimate blur kernels to end-to-end techniques that directly predict sharp images, and includes benchmarking results like PSNR and SSIM on standard datasets such as GOPRO and Kohler.

We inspect all the 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 don't 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 Kohler using various architectures are also provided.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes