Imposing consistency for optical flow estimation

J Jeong, JM Lin, F Porikli… - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Imposing consistency through proxy tasks has been shown to enhance data-driven learning
and enable self-supervision in various tasks. This paper introduces novel and effective …

Image denoising in the deep learning era

S Izadi, D Sutton, G Hamarneh - Artificial Intelligence Review, 2023 - Springer
Over the last decade, the number of digital images captured per day has increased
exponentially, due to the accessibility of imaging devices. The visual quality of photographs …

Unsupervised deep video denoising

DY Sheth, S Mohan, JL Vincent… - Proceedings of the …, 2021 - openaccess.thecvf.com
Deep convolutional neural networks (CNNs) for video denoising are typically trained with
supervision, assuming the availability of clean videos. However, in many applications, such …

Video dynamics prior: An internal learning approach for robust video enhancements

G Shrivastava, SN Lim… - Advances in Neural …, 2024 - proceedings.neurips.cc
In this paper, we present a novel robust framework for low-level vision tasks, including
denoising, object removal, frame interpolation, and super-resolution, that does not require …

L1BSR: Exploiting detector overlap for self-supervised single-image super-resolution of Sentinel-2 L1b imagery

NL Nguyen, J Anger, A Davy… - Proceedings of the …, 2023 - openaccess.thecvf.com
High-resolution satellite imagery is a key element for many Earth monitoring applications.
Satellites such as Sentinel-2 feature characteristics that are favorable for super-resolution …

Self-supervised multi-image super-resolution for push-frame satellite images

NL Nguyen, J Anger, A Davy… - Proceedings of the …, 2021 - openaccess.thecvf.com
Recent constellations of optical satellites are adopting multi-image super-resolution (MISR)
from bursts of push-frame images as a way to increase the resolution and reduce the noise …

Unsupervised deep video denoising with untrained network

H Zheng, T Pang, H Ji - Proceedings of the AAAI Conference on …, 2023 - ojs.aaai.org
Deep learning has become a prominent tool for video denoising. However, most existing
deep video denoising methods require supervised training using noise-free videos …

Realization of a real-time image denoising system for dashboard camera applications

C Yu, LZ Hou - IEEE Transactions on Consumer Electronics, 2022 - ieeexplore.ieee.org
Noise interference during the acquisition of digital images can severely degrade image
quality, particularly for images captured under low-light conditions; however, the removal of …

[HTML][HTML] Deep learning based domain adaptation for mitochondria segmentation on EM volumes

D Franco-Barranco, J Pastor-Tronch… - Computer Methods and …, 2022 - Elsevier
Abstract Background and Objective: Accurate segmentation of electron microscopy (EM)
volumes of the brain is essential to characterize neuronal structures at a cell or organelle …

Recurrent self-supervised video denoising with denser receptive field

Z Wang, Y Zhang, D Zhang, Y Fu - Proceedings of the 31st ACM …, 2023 - dl.acm.org
Self-supervised video denoising has seen decent progress through the use of blind spot
networks. However, under their blind spot constraints, previous self-supervised video …