Learning multiple adverse weather removal via two-stage knowledge learning and multi-contrastive regularization: Toward a unified model

WT Chen, ZK Huang, CC Tsai… - Proceedings of the …, 2022 - openaccess.thecvf.com
In this paper, an ill-posed problem of multiple adverse weather removal is investigated. Our
goal is to train a model with a'unified'architecture and only one set of pretrained weights that …

Laffnet: A lightweight adaptive feature fusion network for underwater image enhancement

HH Yang, KC Huang, WT Chen - 2021 IEEE international …, 2021 - ieeexplore.ieee.org
Underwater image enhancement is an important low-level computer vision task for
autonomous underwater vehicles and remotely operated vehicles to explore and …

Learning temporal-ordered representation for spike streams based on discrete wavelet transforms

J Zhang, S Jia, Z Yu, T Huang - Proceedings of the AAAI Conference on …, 2023 - ojs.aaai.org
Spike camera, a new type of neuromorphic visual sensor that imitates the sampling
mechanism of the primate fovea, can capture photons and output 40000 Hz binary spike …

Dual wavelet attention networks for image classification

Y Yang, L Jiao, X Liu, F Liu, S Yang, L Li… - … on Circuits and …, 2022 - ieeexplore.ieee.org
Global average pooling (GAP) plays an important role in traditional channel attention.
However, there is the disadvantage of insufficient information to use the result of GAP as the …

Dawn: Direction-aware attention wavelet network for image deraining

K Jiang, W Liu, Z Wang, X Zhong, J Jiang… - Proceedings of the 31st …, 2023 - dl.acm.org
Single image deraining aims to remove rain perturbation while restoring the clean
background scene from a rain image. However, existing methods tend to produce blurry and …

Deepopht: medical report generation for retinal images via deep models and visual explanation

JH Huang, CHH Yang, F Liu, M Tian… - Proceedings of the …, 2021 - openaccess.thecvf.com
In this work, we propose an AI-based method that intends to improve the conventional retinal
disease treatment procedure and help ophthalmologists increase diagnosis efficiency and …

HIWDNet: a hybrid image-wavelet domain network for fast magnetic resonance image reconstruction

C Tong, Y Pang, Y Wang - Computers in Biology and Medicine, 2022 - Elsevier
Abstract The application of Magnetic Resonance Imaging (MRI) is limited due to the long
acquisition time of k-space signals. Recently, many deep learning-based MR image …

Counting crowds in bad weather

ZK Huang, WT Chen, YC Chiang, SY Kuo… - arXiv preprint arXiv …, 2023 - arxiv.org
Crowd counting has recently attracted significant attention in the field of computer vision due
to its wide applications to image understanding. Numerous methods have been proposed …

TSRFormer: Transformer based two-stage refinement for single image shadow removal

HE Chang, CH Hsieh, HH Yang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Single-image shadow removal aims to remove undesired shadow information from captured
images. With the development of the deep convolutional neural networks, several methods …

NTIRE 2023 HR nonhomogeneous dehazing challenge report

CO Ancuti, C Ancuti, FA Vasluianu… - Proceedings of the …, 2023 - openaccess.thecvf.com
This study assesses the outcomes of the NTIRE 2023 Challenge on Non-Homogeneous
Dehazing, wherein novel techniques were proposed and evaluated on new image dataset …