What question did this study set out to answer?

The aim is to develop a denoising framework that improves AFM image quality by managing complex noise while preserving nanoscale features.

February 8, 2026

DARA-Net: a dual-path residual attention network for denoising AFM images under complex noise conditions.

Key Points

The aim is to develop a denoising framework that improves AFM image quality by managing complex noise while preserving nanoscale features.
Developed a dual U-shaped GAN architecture with residual attention blocks
Used parallel predictors for feature disentanglement
Created and utilized a dataset of 1000 AFM images with synthetic degradation for training and evaluation
DARA-Net outperformed classical and state-of-the-art methods in PSNR, SSIM, and RMSE
Achieved lower errors in four surface metrics: perimeter, height, roughness, and volume
Demonstrated superior generalization and structural preservation for nanoscale imaging

Abstract

Atomic force microscopy (AFM) images often suffer from random fluctuations, periodic interference, and scanning artifacts. We propose DARA-Net, a denoising framework combining a dual U-shaped GAN architecture with residual attention blocks (RABs) in the decoder stage. Two parallel predictors-one for structural content and one for noise-enable effective feature disentanglement, while the GAN framework enhances detail realism. The fused output benefits from the RAB's ability to suppress complex noise and preserve nanoscale topographical features. A dataset of 1000 in-house AFM images with synthetic degradation was used for training and evaluation. The results show that DARA-Net outperforms classical and state-of-the-art methods in PSNR, SSIM, and RMSE and achieves lower errors in four physical surface metrics (perimeter, height, roughness, and volume), demonstrating superior generalization and structural preservation for nanoscale imaging.

Ask AI

Helpful

Bookmark

View Full Paper