Results 81 to 90 of about 18,768,334 (232)

Mean‐Local Binary Pattern‐Guided Multi‐Attention Network for Low‐Light Image Enhancement

IET Image Processing, Volume 20, Issue 1, January/December 2026.
Low‐light image enhancement struggles with noise amplification, residual dark areas, artefacts and detail loss. This paper presents the MGA‐LLIEN network, which uses M‐LBP for adaptive brightness adjustment and detail recovery while reducing noise and outperforms leading methods in tests. ABSTRACT Low‐light image enhancement faces key challenges: noise
Binxin Tang, Xianchun Zhou, Jiewen Tian, Mengnan Lv, Ying Zhang   +4 more
wiley   +1 more source

See Blue Sky: Deep Image Dehaze Using Paired and Unpaired Training Images

, 2022
The issue of image haze removal has attracted wide attention in recent years. However, most existing haze removal methods cannot restore the scene with clear blue sky, since the color and texture information of the object in the original haze image is ...
Tang, Gaoyang, Zhu, Yingying, Tian, Qi, Zhang, Xiaoyan   +3 more
core  

A Novel Image Dehazing and Assessment Method [PDF]

2019 8th International Conference on Information and Communication Technologies (ICICT), 2019
Accepted in IBA-ICICT ...
Saad Bin Sami, Abdul Muqeet, Humera Tariq   +2 more
openaire   +3 more sources

Enhanced detail & dehaze technique (DDE) for static haze image improvement [PDF]

, 2018
This research is related to the removal of the haze effects from a haze degraded image and enhances the image details. The Enhanced Detail & Dehaze technique (DDE) is proposed in order to satisfy the aim of developing an enhanced method by integrating ...
Danny, Yao Ngo Lung
core   +1 more source

Diffusion Models and Its Applications in Image Dehazing: A Survey

IET Image Processing, Volume 20, Issue 1, January/December 2026.
1.This survey represents the first systematic and comprehensive overview of diffusion model‐based image dehazing, aiming to provide a valuable guide for future researchers and stimulate continued progress in this field. 2.We summarize relevant papers along with their corresponding code links and other resources for image dehazing and all‐in‐one image ...
Liangyu Zhu, Yanzhao Su, Zhigao Cui, Yunwei Lan, Nian Wang, Lanqing Zhang, Yanping Cai   +6 more
wiley   +1 more source

SAASU‐UNet++: A Hybrid Swin Transformer–Based Deep Learning Model for Robust Breast Tumour Segmentation in Ultrasound Images

IET Image Processing, Volume 20, Issue 1, January/December 2026.
This study proposes Swin‐attention‐enhanced atrous spatial pyramid pooling (ASPP)‐attention‐squeeze‐and‐excitation (SE) uncertainty‐aware U‐Net++ (SAASU‐UNet++), a novel hybrid deep learning framework for breast tumour segmentation in ultrasound images.
Rahul Singh, Sheifali Gupta, Ahmad Almogren, Salil Bharany, Ateeq Ur Rehman, Belayneh Matebie Taye, Ayman Altameem   +6 more
wiley   +1 more source

RSDhazer: Residual Shallow‐Deep Network for Efficient Single‐Image Dehazing

IET Image Processing, Volume 20, Issue 1, January/December 2026.
We introduce RSDhazer, a lightweight and efficient end‐to‐end dehazing network designed to handle the complexity of haze removal while maintaining a low computational cost. The proposed RSDhazer comprises three distinct feature extraction blocks that extract shallow and deep features from input images and propagate them through the network without ...
Syeda Rabail Zahra, Farhan Hussain, Tehseen Mazhar, Muhammad Danish Ali, Ghadah Aldehim, Abdul Khader Jilani Saudagar, Muhammad Amir Khan   +6 more
wiley   +1 more source

ICAFormer: An Image Dehazing Transformer Based on Interactive Channel Attention

Sensors
Single image dehazing is a fundamental task in computer vision, aiming to recover a clear scene from a hazy input image. To address the limitations of traditional dehazing algorithms—particularly in global feature association and local detail ...
Yanfei Chen, Tong Yue, Pei An, Hanyu Hong, Tao Liu, Yangkai Liu, Yihui Zhou   +6 more
doaj   +1 more source

TradMS‐ResGAN: A Sequential Multi‐Stage Traditional Framework With Residual Multiscale GAN for Fast and Robust Sand‐Dust Image Restoration

IET Image Processing, Volume 20, Issue 1, January/December 2026.
Sand‐dust degradation significantly reduces visibility, colour fidelity, and structural detail in outdoor imaging systems. This paper proposes TradMS‐ResGAN, a sequential multi‐stage restoration framework that combines a physically interpretable enhancement pipeline with a lightweight multi‐scale residual GAN for refined texture reconstruction and ...
Muhammad Masood, Zahid Hussain, Pablo Otero Roth   +2 more
wiley   +1 more source

Reliable image dehazing by NeRF

Optics Express
Image dehazing is a typical low-level visual task. With the continuous improvement of network performance and the introduction of various prior knowledge, the ability of image dehazing is becoming stronger. However, the existing dehazing methods have problems such as the inability to obtain real shooting datasets, unreliable dehazing processes, and the
Zheyan Jin, Zhihai Xu, Huajun Feng, Qi Li, Yueting Chen   +4 more
openaire   +2 more sources