Research map / Image generation / Image restoration
Mop Moire Patterns Using MopNet
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 multi-scale feature aggregation (ablation) | MopNet baseline · Moire benchmark (ImageNet-based, 135k pairs) | PSNR: 25.377 -> 26.617 | Improved |
| add multi-scale feature aggregation (ablation) | MopNet baseline · Moire benchmark (ImageNet-based, 135k pairs) | SSIM: 0.862 -> 0.882 | Improved |
| add attribute classifier on top of baseline + MS (ablation) | MopNet baseline · Moire benchmark (ImageNet-based, 135k pairs) | PSNR: 26.617 -> 27.076 | Improved |
| add attribute classifier on top of baseline + MS (ablation) | MopNet baseline · Moire benchmark (ImageNet-based, 135k pairs) | SSIM: 0.882 -> 0.884 | Improved |
| add channel-wise edge predictor on top of baseline + MS (ablation) | MopNet baseline · Moire benchmark (ImageNet-based, 135k pairs) | PSNR: 26.617 -> 27.440 | Improved |
| add channel-wise edge predictor on top of baseline + MS (ablation) | MopNet baseline · Moire benchmark (ImageNet-based, 135k pairs) | SSIM: 0.882 -> 0.890 | Improved |
| add both classifier and edge predictor to baseline + MS (full model) (ablation) | MopNet baseline · Moire benchmark (ImageNet-based, 135k pairs) | PSNR: 26.617 -> 27.753 | Improved |
| add both classifier and edge predictor to baseline + MS (full model) (ablation) | MopNet baseline · Moire benchmark (ImageNet-based, 135k pairs) | SSIM: 0.882 -> 0.895 | Improved |
| use moire-specific MopNet instead of DMCNN | MopNet · Moire benchmark (ImageNet-based, 135k pairs) | PSNR: 26.77 -> 27.75 | Improved |
| use moire-specific methods instead of generic DnCNN/VDSR restoration | image restoration · Moire benchmark (ImageNet-based, 135k pairs) | PSNR: 24.54 -> 26.77 | Improved |
| use channel-wise RGB edge maps instead of grayscale edge map for edge predictor (ablation) | edge predictor · Moire benchmark (qualitative) | edge prediction quality | Improved |
| add non-local blocks to edge predictor (ablation) | edge predictor · Moire benchmark (qualitative) | edge prediction quality | Improved |
Closest papers by meaning
- Self-Adaptively Learning to Demoiré from Focused and Defocused Image Pairs (NeurIPS 2020 · similarity 0.86)
- FHDe²Net: Full High Definition Demoireing Network (ECCV 2020 · similarity 0.86)
- Learning Frequency Domain Priors for Image Demoireing (TPAMI 2021 · similarity 0.86)
- Learning Image Demoiréing from Unpaired Real Data (AAAI 2024 · similarity 0.81)
- Direction-Aware Video Demoiréing with Temporal-Guided Bilateral Learning (AAAI 2024 · similarity 0.81)
- UniDemoiré: Towards Universal Image Demoiréing with Data Generation and Synthesis (AAAI 2025 · similarity 0.80)
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.
