computer-vision-5

Single Image Dehazing

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in single-image-dehazing-5

Trend

Dataset

Best Model

Actions

UIEB

RESIDE

Libraries

i

Use these libraries to find single-image-dehazing-5 models and implementations

Datasets

Subtasks

No subtasks available.

Most implemented papers

Contrastive Learning for Compact Single Image Dehazing

Lizhuang Ma, Haiyan Wu, Yanyun Qu, Shaohui Lin, J. Zhou, Ruizhi Qiao, Zhizhong Zhang, Yuan Xie•Sun Apr 18 2021

This paper proposes a novel contrastive regularization (CR) built upon contrastive learning to exploit both the information of hazy images and clear images as negative and positive samples, respectively and develops a compact dehazing network based on autoencoder-like framework.

783

Content

SMOKE

0

Paper Graph

Cycle-Dehaze: Enhanced CycleGAN for Single Image Dehazing

H. K. Ekenel, Deniz Engin, Anil Genç•Sun May 13 2018

This paper presents an end-to-end network, called Cycle-Dehaze, for single image dehazing problem, which does not require pairs of hazy and corresponding ground truth images for training, and improves CycleGAN method both quantitatively and qualitatively.

553 0

Paper Graph

Generic Model-Agnostic Convolutional Neural Network for Single Image Dehazing

Zheng Liu, Botao Xiao, Muhammad Alrabeiah, Keyan Wang, Jun Chen•Thu Oct 04 2018

This paper proposes an end-to-end generative method for image dehazing based on designing a fully convolutional neural network to recognize haze structures in input images and restore clear, haze-free images.

20 0

Paper Graph

FFA-Net: Feature Fusion Attention Network for Single Image Dehazing

Zhiling Wang, Xu Qin, Yuanchao Bai, Xiaodong Xie, Huizhu Jia•Sun Nov 17 2019

The proposed FFA-Net surpasses previous state-of-the-art single image dehazing methods by a very large margin both quantitatively and qualitatively, boosting the best published PSNR metric from 30.23 dB to 36.39 dB on the SOTS indoor test dataset.

1689 0

Paper Graph

Lower Bound on Transmission Using Non-Linear Bounding Function in Single Image Dehazing

S. Raikwar, S. Tapaswi•Thu Feb 27 2020

The visibility of an image captured in poor weather (such as haze, fog, mist, smog) degrades due to scattering of light by atmospheric particles. Single image dehazing (SID) methods are used to restore visibility from a single hazy image. The SID is a challenging problem due to its ill-posed nature. Typically, the atmospheric scattering model (ATSM) is used to solve SID problem. The transmission and atmospheric light are two prime parameters of ATSM. The accuracy and effectiveness of SID depends on accurate value of transmission and atmospheric light. The proposed method translates transmission estimation problem into estimation of the difference between minimum color channel of hazy and haze-free image. The translated problem presents a lower bound on transmission and is used to minimize reconstruction error in dehazing. The lower bound depends upon the bounding function (BF) and a quality control parameter. A non-linear model is then proposed to estimate BF for accurate estimation of transmission. The proposed quality control parameter can be utilized to tune the effect of dehazing. The accuracy obtained by the proposed method for transmission is compared with state of the art dehazing methods. Visual comparison of dehazed images and objective evaluation further validates the effectiveness of the proposed method.

79 0

Paper Graph

Image Dehazing Transformer with Transmission-Aware 3D Position Embedding

Wenqi Ren, Runmin Cong, Chongyi Li, Chunle Guo, Saeed Anwar, Qixin Yan•Tue May 31 2022

Despite single image dehazing has been made promising progress with Convolutional Neural Networks (CNNs), the inherent equivariance and locality of convolution still bottleneck deharing performance. Though Transformer has occupied various computer vision tasks, directly leveraging Transformer for image dehazing is challenging: 1) it tends to result in ambiguous and coarse details that are undesired for image reconstruction; 2) previous position embedding of Transformer is provided in logic or spatial position order that neglects the variational haze densities, which results in the sub-optimal dehazlng performance. The key insight of this study is to investigate how to combine CNN and Transformer for image dehazing. To solve the feature inconsistency issue between Transformer and CNN, we propose to modulate CNN features via learning modulation matrices (i.e., coefficient matrix and bias matrix) conditioned on Transformer features instead of simple feature addition or concatenation. The feature modulation naturally inherits the global context modeling capability of Transformer and the local representation capability of CNN. We bring a haze density-related prior into Trans-former via a novel transmission-aware 3D position embedding module, which not only provides the relative position but also suggests the haze density of different spatial regions. Extensive experiments demonstrate that our method, DeHamer, attains state-of-the-art performance on several image dehazing benchmarks.

453 0

Paper Graph

Densely Connected Pyramid Dehazing Network

Vishal M. Patel, He Zhang•Wed Mar 21 2018

A new end-to-end single image dehazing method, called Densely Connected Pyramid Dehazing Network (DCPDN), which can jointly learn the transmission map, atmospheric light and dehazed all together by directly embedding the atmospheric scattering model into the network.

1049 0

Paper Graph

Adding a benchmark result helps the community track progress.