SAD-Net: a full spectral self-attention detail enhancement network for single image dehazing

• Published in: Scientific reports Vol. 15; no. 1; pp. 11875 - 13
• Main Authors: Niu, Qingjun, Wu, Kun, Zhang, Jialu, Han, Zhenqi, Liu, Lizhuang
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 07.04.2025; Nature Publishing Group; Nature Portfolio
• Subjects: 639/166; 639/705; Convolution; Datasets; Humanities and Social Sciences; multidisciplinary; Science; Science (multidisciplinary); Signal to noise ratio; Surveillance; Wavelet transforms
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-025-92061-1

Single-image dehazing technology plays a significant role in video surveillance and intelligent transportation. However, existing dehazing methods using vanilla convolution only extract features in the temporal domain and lack the ability to capture multi-directional information. To address the aforementioned issues, we design a new full spectral attention-based detail enhancement dehazing network, named SAD-Net. SAD-Net adopts a U-Net-like structure and integrates Spectral Detail Enhancement Convolution (SDEC) and Frequency-Guided Attention (FGA). SDEC combines wavelet transform and difference convolution(DC) to enhance high-frequency features while preserving low-frequency information. FGA detects haze-induced discrepancies and fine-tunes feature modulation. Experimental results show that SAD-Net outperforms six other dehazing networks on the Dense-Haze, NH-Haze, RESIDE and I-Haze datasets. Specifically, it increases the peak signal-to-noise ratio (PSNR) to 17.16 dB on the Dense-Haze dataset, surpassing the current state-of-the-art (SOTA) methods. Additionally, SAD-Net achieves excellent dehazing performance on an external dataset without any prior training.