Self-supervised learning of graph neural networks: A unified review

Y Xie, Z Xu, J Zhang, Z Wang… - IEEE transactions on …, 2022 - ieeexplore.ieee.org
Deep models trained in supervised mode have achieved remarkable success on a variety of
tasks. When labeled samples are limited, self-supervised learning (SSL) is emerging as a …

Applications, promises, and pitfalls of deep learning for fluorescence image reconstruction

C Belthangady, LA Royer - Nature methods, 2019 - nature.com
Deep learning is becoming an increasingly important tool for image reconstruction in
fluorescence microscopy. We review state-of-the-art applications such as image restoration …

Nerf in the dark: High dynamic range view synthesis from noisy raw images

B Mildenhall, P Hedman… - Proceedings of the …, 2022 - openaccess.thecvf.com
Abstract Neural Radiance Fields (NeRF) is a technique for high quality novel view synthesis
from a collection of posed input images. Like most view synthesis methods, NeRF uses …

Plug-and-play image restoration with deep denoiser prior

K Zhang, Y Li, W Zuo, L Zhang… - … on Pattern Analysis …, 2021 - ieeexplore.ieee.org
Recent works on plug-and-play image restoration have shown that a denoiser can implicitly
serve as the image prior for model-based methods to solve many inverse problems. Such a …

Neighbor2neighbor: Self-supervised denoising from single noisy images

T Huang, S Li, X Jia, H Lu, J Liu - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
In the last few years, image denoising has benefited a lot from the fast development of
neural networks. However, the requirement of large amounts of noisy-clean image pairs for …

Blind2unblind: Self-supervised image denoising with visible blind spots

Z Wang, J Liu, G Li, H Han - … of the IEEE/CVF conference on …, 2022 - openaccess.thecvf.com
Real noisy-clean pairs on a large scale are costly and difficult to obtain. Meanwhile,
supervised denoisers trained on synthetic data perform poorly in practice. Self-supervised …

Mm-bsn: Self-supervised image denoising for real-world with multi-mask based on blind-spot network

D Zhang, F Zhou, Y Jiang, Z Fu - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Recent advances in deep learning have been pushing image denoising techniques to a
new level. In self-supervised image denoising, blind-spot network (BSN) is one of the most …

Noise2void-learning denoising from single noisy images

A Krull, TO Buchholz, F Jug - Proceedings of the IEEE/CVF …, 2019 - openaccess.thecvf.com
The field of image denoising is currently dominated by discriminative deep learning methods
that are trained on pairs of noisy input and clean target images. Recently it has been shown …

Recorrupted-to-recorrupted: Unsupervised deep learning for image denoising

T Pang, H Zheng, Y Quan, H Ji - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
Deep denoiser, the deep network for denoising, has been the focus of the recent
development on image denoising. In the last few years, there is an increasing interest in …

Ap-bsn: Self-supervised denoising for real-world images via asymmetric pd and blind-spot network

W Lee, S Son, KM Lee - … of the IEEE/CVF Conference on …, 2022 - openaccess.thecvf.com
Blind-spot network (BSN) and its variants have made significant advances in self-supervised
denoising. Nevertheless, they are still bound to synthetic noisy inputs due to less practical …