Research map / Image generation / Image restoration
Wavelet-Based Dual-Branch Network for Image Demoiréing
Lin Liu, Jianzhuang Liu, Shanxin Yuan, Gregory Slabaugh, Aleš Leonardis, Wengang Zhou, Qi Tian
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 dilation branches (dilated convolutions) (ablation) | WDNet · TIP2018 TestA | PSNR: 26.83 -> 27.88 | Improved |
| add dense blocks in branches (ablation) | WDNet · TIP2018 TestA | PSNR: 27.36 -> 27.88 | Improved |
| add wavelet transform and wavelet loss (ablation) | WDNet · TIP2018 TestA | PSNR: 27.03 -> 27.88 | Improved |
| add DPM module and attention loss (ablation) | WDNet · TIP2018 TestA | PSNR: 27.47 -> 27.88 | Improved |
| use 8-directional DPM instead of 4-directional IRNN (ablation) | WDNet · TIP2018 TestA | PSNR: 27.69 -> 27.88 | Improved |
| add weight maps in DPM (ablation) | WDNet · TIP2018 TestA | PSNR | Improved |
| increase wavelet levels from 1 to 2 (ablation) | WDNet · TIP2018 TestA | PSNR: 27.24 -> 27.88 | Improved |
| increase wavelet levels from 2 to 3 (ablation) | WDNet · TIP2018 TestA | PSNR: 27.88 -> 27.94 | Mixed |
| increase wavelet levels from 2 to 3 (ablation) | WDNet · TIP2018 TestA | SSIM: 0.863 -> 0.843 | Hurt |
| replace MopNet with WDNet | MopNet · TIP2018 TestB | PSNR: 27.75 -> 28.08 | Improved |
| apply WDNet to deraining instead of DAFNet | DAFNet · Rain100h | PSNR: 28.44 -> 28.60 | Improved |
| apply WDNet to deraindrop instead of Quan's method | Quan's · Raindrop800 | PSNR: 31.44 -> 31.75 | Improved |
Closest papers by meaning
- Recaptured Raw Screen Image and Video Demoiréing via Channel and Spatial Modulations (NeurIPS 2023 · similarity 0.89)
- Video Demoireing Using Focused-Defocused Dual-Camera System (TPAMI 2025 · similarity 0.88)
- Direction-Aware Video Demoiréing with Temporal-Guided Bilateral Learning (AAAI 2024 · similarity 0.87)
- UniDemoiré: Towards Universal Image Demoiréing with Data Generation and Synthesis (AAAI 2025 · similarity 0.85)
- Learning Image Demoiréing from Unpaired Real Data (AAAI 2024 · similarity 0.84)
- Efficient Multi-scale Network with Learnable Discrete Wavelet Transform for Blind Motion Deblurring (CVPR 2024 · 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.
