Research map / Image generation / Image restoration
Spatial-Frequency Learning for Scanning Transmission Electron Microscopy Image Enhancement
Hesong Li, Ying Fu, Ziqi Wu, Ruiwen Shao, Tao Zhang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add coordinate-guided frequency branch to spatial-only network (ablation) | SFFN · AtoMix HAADF | PSNR: 27.80 -> 31.60 | Improved |
| add spatial branch to frequency-only network (ablation) | SFFN · AtoMix HAADF | PSNR: 29.40 -> 31.60 | Improved |
| add addition-based cross-domain interaction (ablation) | SFFN · AtoMix HAADF | PSNR: 31.60 -> 31.73 | Improved |
| use learnable fusion instead of no interaction (ablation) | SFFN · AtoMix HAADF | PSNR: 31.60 -> 32.74 | Improved |
| add frequency coordinate channels (ablation) | SFFN · AtoMix HAADF | PSNR: 32.49 -> 32.74 | Improved |
| use learnable fusion and frequency-position guidance instead of SFIN fixed addition | SFFN vs SFIN · AtoMix HAADF | PSNR: 31.95 -> 32.74 | Improved |
| add frequency-domain branch (spatial and frequency networks vs spatial networks) | SFFN · TEMImageNet HAADF | PSNR: 30.28 -> 32.83 | Improved |
| replace fixed addition with SFFN fusion | SFFN vs SFIN · SFIN dataset BF | PSNR: 33.24 -> 35.42 | Improved |
| use SFFN for atom localization instead of SFIN | SFFN vs SFIN · TEMImageNet HAADF | IoU: 0.5987 -> 0.7765 | Improved |
| use SFFN for atom localization instead of SFIN | SFFN vs SFIN · AtoMix BF | IoU: 0.5236 -> 0.5911 | Improved |
| train on AtoMix instead of TEMImageNet or SFIN dataset | SFFN · real STEM images | visual quality | Improved |
Closest papers by meaning
- Noise Calibration and Spatial-Frequency Interactive Network for STEM Image Enhancement (CVPR 2025 · similarity 0.95)
- A Hybrid Frequency-Spatial Domain Model for Sparse Image Reconstruction in Scanning Transmission Electron Microscopy (ICCV 2021 · similarity 0.93)
- Learning Large-Factor EM Image Super-Resolution with Generative Priors (CVPR 2024 · similarity 0.83)
- A Gaussian Filter-Based 3D Registration Method for Series Section Electron Microscopy (AAAI 2025 · similarity 0.82)
- Periodic Materials Generation using Text-Guided Joint Diffusion Model (ICLR 2025 · similarity 0.81)
- Co-PiLOT: Constrained Physics-Informed Latent Optimization for Target-Driven Inverse Design (NeurIPS 2026 · similarity 0.81)
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.
