A bi-stream transformer for single-image dehazing

Deep-learning methods, such as encoder-decoder networks, have achieved impressive results in image dehazing. However, these methods often rely only on synthesized data for training that limits their generalizability to hazy, real-world images. To leverage prior knowledge of haze properties, we propo...

Full description

Saved in:
Bibliographic Details
Main Authors: Mingrui Wang, Jinqiang Yan, Chaoying Wan, Guowei Yang, Teng Yu
Format: Article
Language:English
Published: Electronics and Telecommunications Research Institute (ETRI) 2025-06-01
Series:ETRI Journal
Subjects:
Online Access:https://doi.org/10.4218/etrij.2024-0037
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Deep-learning methods, such as encoder-decoder networks, have achieved impressive results in image dehazing. However, these methods often rely only on synthesized data for training that limits their generalizability to hazy, real-world images. To leverage prior knowledge of haze properties, we propose a bi-encoder structure that integrates a prior-based encoder into a traditional encoder-decoder network. The features from both encoders were fused using a feature enhancement module. We adopted transformer blocks instead of convolutions to model local feature associations. Experimen-tal results demonstrate that our method surpasses state-of-the-art methods for synthesized and actual hazy scenes. Therefore, we believe that our method will be a useful supplement to the collection of current artificial intelligence models and will benefit engineering applications in computer vision.
ISSN:1225-6463
2233-7326