Generative adversarial networks (GANs) for image augmentation in agriculture: A systematic review

Y Lu, D Chen, E Olaniyi, Y Huang - Computers and Electronics in …, 2022 - Elsevier
In agricultural image analysis, optimal model performance is keenly pursued for better
fulfilling visual recognition tasks (eg, image classification, segmentation, object detection …

[HTML][HTML] Medical image super-resolution for smart healthcare applications: A comprehensive survey

S Umirzakova, S Ahmad, LU Khan, T Whangbo - Information Fusion, 2024 - Elsevier
The digital transformation in healthcare, propelled by the integration of deep learning
models and the Internet of Things (IoT), is creating unprecedented opportunities for …

Deep learning for image super-resolution: A survey

Z Wang, J Chen, SCH Hoi - IEEE transactions on pattern …, 2020 - ieeexplore.ieee.org
Image Super-Resolution (SR) is an important class of image processing techniqueso
enhance the resolution of images and videos in computer vision. Recent years have …

Generative adversarial networks (GANs) challenges, solutions, and future directions

D Saxena, J Cao - ACM Computing Surveys (CSUR), 2021 - dl.acm.org
Generative Adversarial Networks (GANs) is a novel class of deep generative models that
has recently gained significant attention. GANs learn complex and high-dimensional …

Video enhancement with task-oriented flow

T Xue, B Chen, J Wu, D Wei, WT Freeman - International Journal of …, 2019 - Springer
Many video enhancement algorithms rely on optical flow to register frames in a video
sequence. Precise flow estimation is however intractable; and optical flow itself is often a …

A review of the deep learning methods for medical images super resolution problems

Y Li, B Sixou, F Peyrin - Irbm, 2021 - Elsevier
Super resolution problems are widely discussed in medical imaging. Spatial resolution of
medical images are not sufficient due to the constraints such as image acquisition time, low …

Photo-realistic single image super-resolution using a generative adversarial network

C Ledig, L Theis, F Huszár… - Proceedings of the …, 2017 - openaccess.thecvf.com
Despite the breakthroughs in accuracy and speed of single image super-resolution using
faster and deeper convolutional neural networks, one central problem remains largely …

[HTML][HTML] A full data augmentation pipeline for small object detection based on generative adversarial networks

B Bosquet, D Cores, L Seidenari, VM Brea… - Pattern Recognition, 2023 - Elsevier
Object detection accuracy on small objects, ie, objects under 32× 32 pixels, lags behind that
of large ones. To address this issue, innovative architectures have been designed and new …

Frame-recurrent video super-resolution

MSM Sajjadi, R Vemulapalli… - Proceedings of the IEEE …, 2018 - openaccess.thecvf.com
Recent advances in video super-resolution have shown that convolutional neural networks
combined with motion compensation are able to merge information from multiple low …

Enhancenet: Single image super-resolution through automated texture synthesis

MSM Sajjadi, B Scholkopf… - Proceedings of the IEEE …, 2017 - openaccess.thecvf.com
Single image super-resolution is the task of inferring a high-resolution image from a single
low-resolution input. Traditionally, the performance of algorithms for this task is measured …