</> Code with Papers by Syntology

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

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

7 Apr 2025Scientific Reports 2025 4archive 2025-07-28

Qingjun Niu， Kun Wu， Jialu Zhang， Zhenqi Han， Lizhuang Liu

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.

PaperPDFCode

Code

niuqj/SAD-Net mentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image DehazingSingle Image Dehazing

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Dehazing Dense-Haze SAD-Net PSNR 17.16 #2 of 5 Archive leaderboard report
Image Dehazing Dense-Haze SAD-Net SSIM 0.55 #2 of 5 Archive leaderboard report
Image Dehazing I-Haze SAD-Net PSNR 21.65 #4 of 4 Archive leaderboard report
Image Dehazing I-Haze SAD-Net SSIM 0.84 #4 of 4 Archive leaderboard report
Image Dehazing NH-HAZE SAD-Net PSNR 20.48 #4 of 4 Archive leaderboard report
Image Dehazing SOTS Indoor SAD-Net PSNR 41.71 #6 of 34 Archive leaderboard report
Image Dehazing SOTS Indoor SAD-Net SSIM 0.993 #6 of 34 Archive leaderboard report
Image Dehazing SOTS Outdoor SAD-Net PSNR 37.78 #10 of 31 Archive leaderboard report
Image Dehazing SOTS Outdoor SAD-Net SSIM 0.990 #10 of 31 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AttentionConvolutionFGASoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections