• Publications
  • Influence
Removing Rain from Single Images via a Deep Detail Network
TLDR
We propose a new deep network architecture for removing rain streaks from individual images based on the deep convolutional neural network (CNN). Expand
  • 286
  • 115
  • PDF
A Weighted Variational Model for Simultaneous Reflectance and Illumination Estimation
TLDR
We propose a weighted variational model to estimate both the reflectance and the illumination from an observed image. Expand
  • 207
  • 66
  • PDF
Clearing the Skies: A Deep Network Architecture for Single-Image Rain Removal
TLDR
We introduce a deep network architecture called DerainNet for removing rain streaks from an image. Expand
  • 268
  • 65
  • PDF
Bayesian Robust Principal Component Analysis
TLDR
A hierarchical Bayesian model is considered for decomposing a matrix into low-rank and sparse components, assuming the observed matrix is a superposition of the two. Expand
  • 236
  • 33
  • PDF
A retinex-based enhancing approach for single underwater image
TLDR
In this paper, a novel retinex-based enhancing approach is proposed to enhance single underwater image. Expand
  • 107
  • 19
  • PDF
A fusion-based enhancing method for weakly illuminated images
TLDR
We propose a straightforward and efficient fusion-based method for enhancing weakly illumination images that uses several mature image processing techniques. Expand
  • 135
  • 18
  • PDF
PanNet: A Deep Network Architecture for Pan-Sharpening
TLDR
We propose a deep network architecture for the pan-sharpening problem called PanNet. Expand
  • 75
  • 18
  • PDF
A Probabilistic Method for Image Enhancement With Simultaneous Illumination and Reflectance Estimation
TLDR
In this paper, a new probabilistic method for image enhancement that estimates illumination and reflectance simultaneously is proposed in the linear domain. Expand
  • 113
  • 16
  • PDF
Remote Sensing Image Enhancement Using Regularized-Histogram Equalization and DCT
TLDR
In this letter, an effective enhancement method for remote sensing images is introduced to improve the global contrast and the local details. Expand
  • 68
  • 12
  • PDF
Lightweight Pyramid Networks for Image Deraining
TLDR
We propose a lightweight deep network that is based on the classical Gaussian–Laplacian pyramid for single-image deraining. Expand
  • 48
  • 11
  • PDF