K
Ke Xu
Researcher at Shanghai Jiao Tong University
Publications - 52
Citations - 1426
Ke Xu is an academic researcher from Shanghai Jiao Tong University. The author has contributed to research in topics: Computer science & Convolutional neural network. The author has an hindex of 11, co-authored 43 publications receiving 600 citations. Previous affiliations of Ke Xu include City University of Hong Kong & Dalian University of Technology.
Papers
More filters
Proceedings ArticleDOI
Spatial Attentive Single-Image Deraining With a High Quality Real Rain Dataset
TL;DR: A semi-automatic method that incorporates temporal priors and human supervision to generate a high-quality clean image from each input sequence of real rain images is proposed, and a novel SPatial Attentive Network (SPANet) is proposed to remove rain streaks in a local-to-global manner.
Proceedings ArticleDOI
Learning to Restore Low-Light Images via Decomposition-and-Enhancement
TL;DR: A frequency-based decompositionand- enhancement model that first learns to recover image objects in the low-frequency layer and then enhances high-frequency details based on the recovered image objects and outperforms state-of-the-art approaches in enhancing practical noisy low-light images.
Posted Content
Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset.
TL;DR: Wang et al. as mentioned in this paper proposed a semi-automatic method that incorporates temporal priors and human supervision to generate a high-quality clean image from each input sequence of real rain images.
Proceedings ArticleDOI
Image Correction via Deep Reciprocating HDR Transformation
TL;DR: Zhang et al. as discussed by the authors formulated the image correction task as an HDR transformation process and proposed a novel approach called Deep Reciprocating HDR Transformation (DRHT), which first reconstruct the missing details in the HDR domain and then perform tone mapping on the predicted HDR data to generate the output LDR image with the recovered details.
Journal ArticleDOI
DRFN: Deep Recurrent Fusion Network for Single-Image Super-Resolution With Large Factors
TL;DR: In this article, a deep recurrent fusion network (DRFN) was proposed, which utilizes transposed convolution instead of bicubic interpolation for upsampling and integrates different-level features extracted from recurrent residual blocks to reconstruct the final HR images.