Towards unified deep image deraining: A survey and a new benchmark

X Chen, J Pan, J Dong, J Tang - arxiv preprint arxiv:2310.03535, 2023 - arxiv.org
Recent years have witnessed significant advances in image deraining due to the kinds of
effective image priors and deep learning models. As each deraining approach has …

Domain adaptive object detection for autonomous driving under foggy weather

J Li, R Xu, J Ma, Q Zou, J Ma… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Most object detection methods for autonomous driving usually assume a onsistent feature
distribution between training and testing data, which is not always the case when weathers …

A survey of deep learning approaches to image restoration

J Su, B Xu, H Yin - Neurocomputing, 2022 - Elsevier
In this paper, we present an extensive review on deep learning methods for image
restoration tasks. Deep learning techniques, led by convolutional neural networks, have …

Auto-exposure fusion for single-image shadow removal

L Fu, C Zhou, Q Guo, F Juefei-Xu… - Proceedings of the …, 2021 - openaccess.thecvf.com
Shadow removal is still a challenging task due to its inherent background-dependent and
spatial-variant properties, leading to unknown and diverse shadow patterns. Even powerful …

Misf: Multi-level interactive siamese filtering for high-fidelity image inpainting

X Li, Q Guo, D Lin, P Li, W Feng… - Proceedings of the …, 2022 - openaccess.thecvf.com
Although achieving significant progress, existing deep generative inpainting methods still
show low generalization across different scenes. As a result, the generated images usually …

Not just streaks: Towards ground truth for single image deraining

Y Ba, H Zhang, E Yang, A Suzuki, A Pfahnl… - … on Computer Vision, 2022 - Springer
We propose a large-scale dataset of real-world rainy and clean image pairs and a method to
remove degradations, induced by rain streaks and rain accumulation, from the image. As …

Weatherstream: Light transport automation of single image deweathering

H Zhang, Y Ba, E Yang, V Mehra… - Proceedings of the …, 2023 - openaccess.thecvf.com
Today single image deweathering is arguably more sensitive to the dataset type, rather than
the model. We introduce WeatherStream, an automatic pipeline capturing all real-world …

SAPNet: Segmentation-aware progressive network for perceptual contrastive deraining

S Zheng, C Lu, Y Wu, G Gupta - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Deep learning algorithms have recently achieved promising deraining performances on
both the natural and synthetic rainy datasets. As an essential low-level pre-processing …

Local and global knowledge distillation with direction-enhanced contrastive learning for single-image deraining

Y Luo, Q Huang, J Ling, K Lin, T Zhou - Knowledge-Based Systems, 2023 - Elsevier
Single image deraining (SID) is a challenging problem since the rainy images contain a
variety of backgrounds with rain streaks of different directions and densities. Though …

DeepRepair: Style-Guided Repairing for Deep Neural Networks in the Real-World Operational Environment

B Yu, H Qi, Q Guo, F Juefei-Xu, X **e… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Deep neural networks (DNNs) are continuously expanding their application to various
domains due to their high performance. Nevertheless, a well-trained DNN after deployment …