Deep image prior

D Ulyanov, A Vedaldi… - Proceedings of the IEEE …, 2018 - openaccess.thecvf.com
Deep convolutional networks have become a popular tool for image generation and
restoration. Generally, their excellent performance is imputed to their ability to learn realistic …

Scale-recurrent network for deep image deblurring

X Tao, H Gao, X Shen, J Wang… - Proceedings of the IEEE …, 2018 - openaccess.thecvf.com
In single image deblurring, the``coarse-to-fine''scheme, ie gradually restoring the sharp
image on different resolutions in a pyramid, is very successful in both traditional optimization …

Deep image deblurring: A survey

K Zhang, W Ren, W Luo, WS Lai, B Stenger… - International Journal of …, 2022 - Springer
Image deblurring is a classic problem in low-level computer vision with the aim to recover a
sharp image from a blurred input image. Advances in deep learning have led to significant …

“zero-shot” super-resolution using deep internal learning

A Shocher, N Cohen, M Irani - Proceedings of the IEEE …, 2018 - openaccess.thecvf.com
Deep Learning has led to a dramatic leap in Super-Resolution (SR) performance in the past
few years. However, being supervised, these SR methods are restricted to specific training …

Deep image prior

V Lempitsky, A Vedaldi… - 2018 IEEE/CVF …, 2018 - ieeexplore.ieee.org
Deep convolutional networks have become a popular tool for image generation and
restoration. Generally, their excellent performance is imputed to their ability to learn realistic …

Mutual affine network for spatially variant kernel estimation in blind image super-resolution

J Liang, G Sun, K Zhang… - Proceedings of the …, 2021 - openaccess.thecvf.com
Existing blind image super-resolution (SR) methods mostly assume blur kernels are spatially
invariant across the whole image. However, such an assumption is rarely applicable for real …

Event-based fusion for motion deblurring with cross-modal attention

L Sun, C Sakaridis, J Liang, Q Jiang, K Yang… - European conference on …, 2022 - Springer
Traditional frame-based cameras inevitably suffer from motion blur due to long exposure
times. As a kind of bio-inspired camera, the event camera records the intensity changes in …

State-of-the-art approaches for image deconvolution problems, including modern deep learning architectures

M Makarkin, D Bratashov - Micromachines, 2021 - mdpi.com
In modern digital microscopy, deconvolution methods are widely used to eliminate a number
of image defects and increase resolution. In this review, we have divided these methods into …

Multi-temporal recurrent neural networks for progressive non-uniform single image deblurring with incremental temporal training

D Park, DU Kang, J Kim, SY Chun - European Conference on Computer …, 2020 - Springer
Blind non-uniform image deblurring for severe blurs induced by large motions is still
challenging. Multi-scale (MS) approach has been widely used for deblurring that …

Pyramid attention network for image restoration

Y Mei, Y Fan, Y Zhang, J Yu, Y Zhou, D Liu… - International Journal of …, 2023 - Springer
Self-similarity refers to the image prior widely used in image restoration algorithms that small
but similar patterns tend to occur at different locations and scales. However, recent …