Research map / Image generation / Image restoration
FHDe²Net: Full High Definition Demoireing Network
Bin He, Ce Wang, Boxin Shi, Ling-Yu Duan
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 Global Demoireing Network (GDN) (ablation) | FHDe2Net · FHDMi test | PSNR: 18.5392 -> 22.9300 | Improved |
| add Global Demoireing Network (GDN) (ablation) | FHDe2Net · FHDMi test | LPIPS: 0.2577 -> 0.1688 | Improved |
| add Local Refinement Network (LRN) (ablation) | FHDe2Net · FHDMi test | PSNR: 20.3143 -> 22.9300 | Improved |
| add Local Refinement Network (LRN) (ablation) | FHDe2Net · FHDMi test | SSIM: 0.7652 -> 0.7885 | Improved |
| add Frequency based Disentangling Network (FDN) (ablation) | FHDe2Net · FHDMi test | PSNR: 22.9017 -> 22.9300 | Improved |
| add Frequency based Disentangling Network (FDN) (ablation) | FHDe2Net · FHDMi test | LPIPS: 0.2582 -> 0.1688 | Improved |
| add Fusion Refining Network (FRN) (ablation) | FHDe2Net · FHDMi test | PSNR: 22.4153 -> 22.9300 | Improved |
| add Fusion Refining Network (FRN) (ablation) | FHDe2Net · FHDMi test | LPIPS: 0.2101 -> 0.1688 | Improved |
| FHDe2Net instead of MopNet | MopNet · FHDMi test | PSNR: 22.7559 -> 22.9300 | Improved |
| FHDe2Net instead of MopNet | MopNet · FHDMi test | SSIM: 0.7958 -> 0.7885 | Hurt |
| FHDe2Net instead of MopNet | MopNet · FHDMi test | LPIPS: 0.1794 -> 0.1688 | Improved |
| FHDe2Net (GDN only, fine-tuned) instead of MopNet | MopNet · TIP18 benchmark | PSNR: 27.7500 -> 27.7850 | Improved |
Closest papers by meaning
- RIFLE: Removal of Image Flicker-Banding via Latent Diffusion Enhancement (NeurIPS 2026 · similarity 0.84)
- Direction-Aware Video Demoiréing with Temporal-Guided Bilateral Learning (AAAI 2024 · similarity 0.83)
- Bricker to BRACE: A Bracket Exposure RAW Dataset and Restoration Model for Flicker-Banding (NeurIPS 2026 · similarity 0.83)
- Learning Image Demoiréing from Unpaired Real Data (AAAI 2024 · similarity 0.83)
- UniDemoiré: Towards Universal Image Demoiréing with Data Generation and Synthesis (AAAI 2025 · similarity 0.83)
- Efficient RAW Image Deblurring with Adaptive Frequency Modulation (NeurIPS 2025 · similarity 0.83)
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.
