Advancing Real-World Image Dehazing: Perspective, Modules, and Training
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-12 · 46 (12) · 9303-9320
DOI: 10.1109/tpami.2024.3416731 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-12. Verfasst von Yuxin Feng und 5 weiteren Autor:innen. Die Arbeit wurde bisher 114-mal zitiert (Crossref) und nennt 86 Literaturangaben. Gefördert von: Basic and Applied Basic Research Foundation of Guangdong Province, Guangxi Science and Technology Plan, China Postdoctoral Science Foundation.
Abstract (Originalsprache)
Restoring high-quality images from degraded hazy observations is a fundamental and essential task in the field of computer vision. While deep models have achieved significant success with synthetic data, their effectiveness in real-world scenarios remains uncertain. To improve adaptability in real-world environments, we construct an entirely new computational framework by making efforts from three key aspects: imaging perspective, structural modules, and training strategies. To simulate the often-overlooked multiple degradation attributes found in real-world hazy images, we develop a new hazy imaging model that encapsulates multiple degraded factors, assisting in bridging the domain gap between synthetic and real-world image spaces. In contrast to existing approaches that primarily address the inverse imaging process, we design a new dehazing network following the "localization-and-removal" pipeline. The degradation localization module aims to assist in network capture discriminative haze-related feature information, and the degradation removal module focuses on eliminating dependencies between features by learning a weighting matrix of training samples, thereby avoiding spurious correlations of extracted features in existing deep methods. We also define a new Gaussian perceptual contrastive loss to further constrain the network to update in the direction of the natural dehazing. Regarding multiple full/no-reference image quality indicators and subjective visual effects on challenging RTTS, URHI, and Fattal real hazy datasets, the proposed method has superior performance and is better than the current state-of-the-art methods.
Förderung
- Basic and Applied Basic Research Foundation of Guangdong Province
- Guangxi Science and Technology Plan
- China Postdoctoral Science Foundation
Zitieren
APA
Feng, Y., Ma, L., Meng, X., Zhou, F., Liu, R., & Su, Z. (2024). Advancing Real-World Image Dehazing: Perspective, Modules, and Training. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12), 9303-9320. https://doi.org/10.1109/tpami.2024.3416731
Vancouver
Feng Y, Ma L, Meng X, Zhou F, Liu R, Su Z. Advancing Real-World Image Dehazing: Perspective, Modules, and Training. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(12):9303-9320. doi:10.1109/tpami.2024.3416731
BibTeX
@article{Feng2024,
author = {Feng, Yuxin and Ma, Long and Meng, Xiaozhe and Zhou, Fan and Liu, Risheng and Su, Zhuo},
title = {Advancing Real-World Image Dehazing: Perspective, Modules, and Training},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2024},
volume = {46},
number = {12},
pages = {9303--9320},
doi = {10.1109/tpami.2024.3416731}
}
EUVIMED