Towards unified deep image deraining: A survey and a new benchmark
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 …
effective image priors and deep learning models. As each deraining approach has …
Domain adaptive object detection for autonomous driving under foggy weather
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 …
distribution between training and testing data, which is not always the case when weathers …
A survey of deep learning approaches to image restoration
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 …
restoration tasks. Deep learning techniques, led by convolutional neural networks, have …
Auto-exposure fusion for single-image shadow removal
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 …
spatial-variant properties, leading to unknown and diverse shadow patterns. Even powerful …
Misf: Multi-level interactive siamese filtering for high-fidelity image inpainting
Although achieving significant progress, existing deep generative inpainting methods still
show low generalization across different scenes. As a result, the generated images usually …
show low generalization across different scenes. As a result, the generated images usually …
Not just streaks: Towards ground truth for single image deraining
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 …
remove degradations, induced by rain streaks and rain accumulation, from the image. As …
Weatherstream: Light transport automation of single image deweathering
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 …
the model. We introduce WeatherStream, an automatic pipeline capturing all real-world …
SAPNet: Segmentation-aware progressive network for perceptual contrastive deraining
Deep learning algorithms have recently achieved promising deraining performances on
both the natural and synthetic rainy datasets. As an essential low-level pre-processing …
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 …
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
Deep neural networks (DNNs) are continuously expanding their application to various
domains due to their high performance. Nevertheless, a well-trained DNN after deployment …
domains due to their high performance. Nevertheless, a well-trained DNN after deployment …