ZRDNet: zero-reference image defogging by physics-based decomposition–reconstruction mechanism and perception fusion

Zi-Xin Li; Yu‐Long Wang; Qinglong Qinglong Han; Peng Chen

doi:10.1007/s00371-023-03109-0

Back

ZRDNet: zero-reference image defogging by physics-based decomposition–reconstruction mechanism and perception fusion

The Visual Computer 40(8): 5357-5374

Article 2023 English

Abstract

1 min read

This paper investigates challenging fully unsupervised defogging problems, i.e., how to remove fog by feeding only foggy images in deep neural networks rat

Discussion(0)

No comments yet. Be the first to comment.

Related publications

Article2023

Image Watermarking Based Data Hiding by Discrete Wavelet Transform Quantization Model with Convolutional Generative Adversarial Architectures

C. Annadurai, I. Nelson, K. Nirmala Devi, R. Manikandan, Amir Gandomi

Applied Sciences

Preprint2019

Semi-Supervised Self-Growing Generative Adversarial Networks for Image Recognition

Haoqian Wang, Zhiwei Xu, Jun Xu, Wangpeng An, Lei Zhang, Qionghai Dai

Preprint2021

Subspace Decomposition based DNN algorithm for elliptic type multi-scale\n PDEs

Xian Li, Zhi‐Qin John Xu, Lei Zhang

Article2023

The role of 3D data in CNN-based object detection

Juan C. Peña, Eberto Benjumea, Raúl Vargas, Lenny A. Romero, Alberto Patino Vanegas, Andrés G. Marrugo

Preprint2025

Neural Network-Based Spatial Autocorrelation Representation for Deep Learning-Driven Geospatial Object Detection from 3D Point Clouds: A Case Study with Urban and Rural Scenes

Tianyang Chen, Wenwu Tang, Shenen Chen, Craig Allan