AI Paper Atlas

Research map / Image generation / Image restoration

Statistical Characteristic-Guided Denoising for Rapid High-Resolution Transmission Electron Microscopy Imaging

Hesong Li, Ziqi Wu, Ruiwen Shao, Ying Fu

CVPR 2026 · Image generation › Image restoration · approach: Diffusion-based universal restoration · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add spatial deviation-guided weighting (SDGW) (ablation)SCGN without SDGW · NUC datasetPSNR (dB): 26.23 -> 26.55Improved
add frequency band-guided weighting (FBGW) with position embedding (ablation)SCGN with SDGW only · NUC datasetPSNR (dB): 26.19 -> 26.55Improved
use FBGW instead of channel attention (ablation)SCGN · NUC datasetPSNR (dB): 26.24 -> 26.55Improved
add position embedding to FBGW (ablation)SCGN · NUC datasetPSNR (dB): 26.48 -> 26.55Improved
train on NUC (noise-calibrated, disordered) rather than TEMImageNet or SFIN dataset (ablation)supervised denoisers on real HRTEM data · Real Pt nucleation HRTEM framesqualitative atom recoveryImproved
SCGN versus SFIN on NUCdenoising network · NUC datasetPSNR (dB): 25.70 -> 26.55Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy