W
Wenqi Ren
Researcher at Chinese Academy of Sciences
Publications - 148
Citations - 8475
Wenqi Ren is an academic researcher from Chinese Academy of Sciences. The author has contributed to research in topics: Computer science & Deblurring. The author has an hindex of 26, co-authored 111 publications receiving 3914 citations. Previous affiliations of Wenqi Ren include Tianjin University & Jimei University.
Papers
More filters
Book ChapterDOI
Single Image Dehazing via Multi-scale Convolutional Neural Networks
TL;DR: A multi-scale deep neural network for single-image dehazing by learning the mapping between hazy images and their corresponding transmission maps by combining a coarse-scale net which predicts a holistic transmission map based on the entire image, and a fine-scale network which refines results locally.
Journal ArticleDOI
Benchmarking Single-Image Dehazing and Beyond
TL;DR: In this article, the authors present a comprehensive study and evaluation of existing single image dehazing algorithms, using a new large-scale benchmark consisting of both synthetic and real-world hazy images, called Realistic Single-Image DEhazing (RESIDE).
Journal ArticleDOI
An Underwater Image Enhancement Benchmark Dataset and Beyond
TL;DR: This paper constructs an Underwater Image Enhancement Benchmark (UIEB) including 950 real-world underwater images, 890 of which have the corresponding reference images and proposes an underwater image enhancement network (called Water-Net) trained on this benchmark as a baseline, which indicates the generalization of the proposed UIEB for training Convolutional Neural Networks (CNNs).
Proceedings ArticleDOI
Gated Fusion Network for Single Image Dehazing
TL;DR: An efficient algorithm to directly restore a clear image from a hazy input using an end-to-end trainable neural network that consists of an encoder and a decoder is proposed.
Journal ArticleDOI
Low-Light Image Enhancement via a Deep Hybrid Network
TL;DR: A novel spatially variant recurrent neural network (RNN) is proposed as an edge stream to model edge details, with the guidance of another auto-encoder, to enhance the visibility of degraded images.