Physics-Guided Multi-Channel Restoration for Efficient and Accurate Atomic Force Microscopy Imaging.
8 affiliations
- 1School of Advanced Materials Science and Engineering, Sungkyunkwan University, Suwon, Republic of Korea.
- 2Department of Applied Data Science, Sungkyunkwan University (SKKU), Suwon, Republic of Korea.
- 3Department of Semiconductor and Display Engineering, Sungkyunkwan University (SKKU), Suwon, Republic of Korea.
- 4Department of Materials Science and Engineering, Korea University, Seoul, Republic of Korea.
- 5Samsung Advanced Institute of Technology, Suwon, Republic of Korea.
- 6National Nano Fab Center (NNFC), Daejeon, Republic of Korea.
- 7School of Materials Science and Engineering, Yeungnam University, Gyeongsan, Gyeongbuk, Republic of Korea.
- 8Korea Research Institute of Standards and Science (KRISS), Daejeon, Republic of Korea.
Abstract
Scientific imaging instruments often acquire multiple physically complementary signals within a single measurement. In atomic force microscopy (AFM), high-throughput imaging requires higher scan speeds, however, image quality is fundamentally limited by multiple distortions. These artifacts are further amplified for sharp nano/microstructures, making accurate image restoration inherently challenging. Most deep learning-based approaches rely on a single primary channel and improve performance by increasing model complexity or training data. Here, we introduce a physics-guided multi-channel input approach for AFM that utilizes co-acquired auxiliary signals to improve image restoration efficiency and accuracy. We construct a four co-acquired channel input, each containing complementary physical information. By integrating these channels into a lightweight convolutional neural network, the proposed approach significantly improves restoration quality with minimal additional parameters. At a scan rate of 7.0 Hz, the four-channel DnCNN achieved higher reconstruction accuracy than a single-channel Restormer with approximately 47 times as many parameters, while providing approximately 24 times faster inference. Across the evaluated EFM and PFM conditions, four-channel inputs reduced the training-patch requirement by approximately two to three times at matched PSNR.
Related
- Reference-guided defocus estimation enables physics-guided image restoration in deep ultraviolet wafer microscopy
- Acquisition-inspired motion artifact modeling and degradation-consistent diffusion restoration in photoacoustic microscopy
- Single-step initialization of a 16-channel silicon nitride DWDM demultiplexer using a physics-informed digital twin
- Accurate and efficient calculation of atomic forces in solids with non-self-consistent hybrid functionals
- Physics-Grounded Simulation Enables Zero-Shot Molecular and Reaction Analysis in Scanning Tunneling Microscopy
BibTeX
@article{sung2026physicsguided,
title = {{Physics-Guided Multi-Channel Restoration for Efficient and Accurate Atomic Force Microscopy Imaging.}},
author = {Jaeuk Sung and Hongseok Kim and Seungjae Heo and Jin Tae Moon and Jangwoo Ko and Panithan Sriboriboon and Dong-Gyu Lee and Sanghyun Jo and Hee Han and Jungho Ryu and Woo Lee and Jinseong Heo and Hyun-Cheol Song and Yunseok Kim},
journal = {Advanced science (Weinheim, Baden-Wurttemberg, Germany)},
year = {2026},
month = oct,
doi = {10.1002/advs.78289},
url = {https://europepmc.org/article/MED/42893507},
note = {CC BY},
}
RIS
TY - JOUR
TI - Physics-Guided Multi-Channel Restoration for Efficient and Accurate Atomic Force Microscopy Imaging.
AU - Jaeuk Sung
AU - Hongseok Kim
AU - Seungjae Heo
AU - Jin Tae Moon
AU - Jangwoo Ko
AU - Panithan Sriboriboon
AU - Dong-Gyu Lee
AU - Sanghyun Jo
AU - Hee Han
AU - Jungho Ryu
AU - Woo Lee
AU - Jinseong Heo
AU - Hyun-Cheol Song
AU - Yunseok Kim
PY - 2026
DA - 2026/10/18
JO - Advanced science (Weinheim, Baden-Wurttemberg, Germany)
DO - 10.1002/advs.78289
UR - https://europepmc.org/article/MED/42893507
AB - Scientific imaging instruments often acquire multiple physically complementary signals within a single measurement. In atomic force microscopy (AFM), high-throughput imaging requires higher scan speeds, however, image quality is fundamentally limited by multiple distortions. These artifacts are further amplified for sharp nano/microstructures, making accurate image restoration inherently challenging. Most deep learning-based approaches rely on a single primary channel and improve performance by increasing model complexity or training data. Here, we introduce a physics-guided multi-channel input approach for AFM that utilizes co-acquired auxiliary signals to improve image restoration efficiency and accuracy. We construct a four co-acquired channel input, each containing complementary physical information. By integrating these channels into a lightweight convolutional neural network, the proposed approach significantly improves restoration quality with minimal additional parameters. At a scan rate of 7.0 Hz, the four-channel DnCNN achieved higher reconstruction accuracy than a single-channel Restormer with approximately 47 times as many parameters, while providing approximately 24 times faster inference. Across the evaluated EFM and PFM conditions, four-channel inputs reduced the training-patch requirement by approximately two to three times at matched PSNR.
SN - 2198-3844
ER -