Previous raw image-based low-light image enhancement methods predominant...
Deep neural networks (DNNs) have found widespread applications in
interp...
While raw images have distinct advantages over sRGB images, e.g., linear...
File fragment classification (FFC) on small chunks of memory is essentia...
In this paper, we study a real-world JPEG image restoration problem with...
While raw images exhibit advantages over sRGB images (e.g., linearity an...
Even though virtual testing of Autonomous Vehicles (AVs) has been well
r...
A protector is placed in front of the camera lens for mobile devices to ...
In this paper, we introduce the notion of Cooperative Perception Error M...
In this paper, we propose a three-stream adaptive fusion network named
T...
To enhance low-light images to normally-exposed ones is highly ill-posed...
Domain generalization aims to learn an invariant model that can generali...
Vehicle re-identification (Re-ID) is to retrieve images of the same vehi...
High Dynamic Range (HDR) imaging via multi-exposure fusion is an importa...
Though convolutional neural networks are widely used in different tasks,...
State-of-the-art deep neural networks are sensitive to small input
pertu...
The CenterTrack tracking algorithm achieves state-of-the-art tracking
pe...
Re-ranking utilizes contextual information to optimize the initial ranki...
In this paper, we propose a simple yet effective crowd counting and
loca...
In this paper, we propose a real-time and accurate automatic license pla...
Deep neural networks (DNN) have shown great success in many computer vis...
In this paper, we propose a novel self-training approach which enables a...
Various architectures (such as GoogLeNets, ResNets, and DenseNets) have ...
Regularization is commonly used in machine learning for alleviating
over...
The light field faithfully records the spatial and angular configuration...
Ideally, what confuses neural network should be confusing to humans. How...
Vision based haze density estimation is of practical implications for th...
Light field (LF) cameras provide perspective information of scenes by ta...
Idling vehicles waste energy and pollute the environment through exhaust...
Outdoor vision-based systems suffer from atmospheric turbulences, and ra...
Rain removal is important for improving the robustness of outdoor vision...
This paper proposes a new method called Multimodal RNNs for RGB-D scene
...
Depth estimation is a fundamental problem for light field photography
ap...
Recent imaging technologies are rapidly evolving for sampling richer and...