Lightweight single-image dehazing via haze-aware attention and discrete wavelet transform
Discover Computing · 02.05.2026 · 29 (1)
DOI: 10.1007/s10791-026-10150-9 ↗Kurz gefasst
Fachartikel in der Zeitschrift Discover Computing, online erschienen am 02.05.2026. Verfasst von Yuanyuan Fan und 1 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Single-image dehazing is essential for safety-critical vision systems, yet existing CNN-based methods are often too heavy for edge devices or fail to adapt to spatially varying haze density. This paper introduces HazeWaveNet, a lightweight wavelet-based dehazing network that leverages discrete wavelet transform (DWT) to separate high- and low-frequency components, targeting haze-affected regions while preserving details. A haze-trend guidance mechanism, derived from the dark-channel prior, generates adaptive weight maps that modulate features through factorized convolutions and haze-aware attention modules. Extensive experiments on synthetic and real-world datasets demonstrate that HazeWaveNet achieves competitive performance with significantly lower computational requirements, making it suitable for real-time deployment on resource-constrained platforms.
Zitieren
APA
Fan, Y., & Mi, X. (2026). Lightweight single-image dehazing via haze-aware attention and discrete wavelet transform. Discover Computing, 29(1). https://doi.org/10.1007/s10791-026-10150-9
Vancouver
Fan Y, Mi X. Lightweight single-image dehazing via haze-aware attention and discrete wavelet transform. Discover Computing. 2026;29(1). doi:10.1007/s10791-026-10150-9
BibTeX
@article{Fan2026,
author = {Fan, Yuanyuan and Mi, Xifeng},
title = {Lightweight single-image dehazing via haze-aware attention and discrete wavelet transform},
journal = {Discover Computing},
year = {2026},
volume = {29},
number = {1},
doi = {10.1007/s10791-026-10150-9}
}
EUVIMED