6 papers
DURRNet: Deep Unfolded Single Image Reflection Removal Network
Jun-Jie Huang, Tianrui Liu, Zhixiong Yang +3
Single image reflection removal problem aims to divide a reflection-contaminated image into a transmission image and a reflection image. It is a canonical blind source separation p…
LINN: Lifting Inspired Invertible Neural Network for Image Denoising
Jun-Jie Huang, Pier Luigi Dragotti
In this paper, we propose an invertible neural network for image denoising (DnINN) inspired by the transform-based denoising framework. The proposed DnINN consists of an invertible…
Learning Deep Analysis Dictionaries for Image Super-Resolution
Jun-Jie Huang, Pier Luigi Dragotti
Inspired by the recent success of deep neural networks and the recent efforts to develop multi-layer dictionary models, we propose a Deep Analysis dictionary Model (DeepAM) which i…
Coupled Network for Robust Pedestrian Detection with Gated Multi-Layer Feature Extraction and Deformable Occlusion Handling
Tianrui Liu, Wenhan Luo, Lin Ma +3
Pedestrian detection methods have been significantly improved with the development of deep convolutional neural networks. Nevertheless, detecting small-scaled pedestrians and occlu…
Gated Multi-layer Convolutional Feature Extraction Network for Robust Pedestrian Detection
Tianrui Liu, Jun-Jie Huang, Tianhong Dai +2
Pedestrian detection methods have been significantly improved with the development of deep convolutional neural networks. Nevertheless, robustly detecting pedestrians with a large…
Reconstruction of FRI Signals using Deep Neural Network Approaches
Vincent C. H. Leung, Jun-Jie Huang, Pier Luigi Dragotti
Finite Rate of Innovation (FRI) theory considers sampling and reconstruction of classes of non-bandlimited continuous signals that have a small number of free parameters, such as a…