Research map / Video / Video segmentation and tracking
Recaptured Raw Screen Image and Video Demoiréing via Channel and Spatial Modulations
Huanjing Yue, Yijia Cheng, Xin Liu, Jingyu Yang
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 spatial modulation (SMod) to baseline (ablation) | Baseline · RawVDemoire video | PSNR: 27.963 -> 28.439 | Improved |
| add SMod with color-mixed feature replacing color-separated (SMod+) (ablation) | Baseline+SMod · RawVDemoire video | PSNR: 28.439 -> 28.498 | No clear effect |
| use channel-spatial modulation CSMod instead of SMod (ablation) | Baseline+SMod · RawVDemoire video | PSNR: 28.439 -> 28.706 | Improved |
| add SMod (ablation) | Baseline · RawVDemoire video | LPIPS: 0.0914 -> 0.0939 | Hurt |
| remove VGG perceptual loss (ablation) | Complete model · RawVDemoire video | PSNR: 28.706 -> 28.069 | Hurt |
| remove color loss (ablation) | Complete model · RawVDemoire video | PSNR: 28.706 -> 28.642 | Hurt |
| remove multi-scale loss (ablation) | Complete model · RawVDemoire video | PSNR: 28.706 -> 27.455 | Hurt |
| remove VGG loss (ablation) | Complete model · RawVDemoire video | LPIPS: 0.0904 -> 0.1160 | Hurt |
| raw-input retraining of MBCNN | MBCNN · Raw image demoireing | PSNR: 26.667 -> 27.187 | Improved |
| raw-input retraining of UHDM | UHDM · RawVDemoire video | PSNR: 26.823 -> 25.642 | Hurt |
| raw-input retraining of VDMoire | VDMoire · RawVDemoire video | PSNR: 27.277 -> 27.747 | Improved |
| raw-input retraining of EDVR | EDVR · RawVDemoire video | PSNR: 26.785 -> 27.285 | Improved |
Closest papers by meaning
- Image Demoireing in RAW and sRGB Domains (ECCV 2024 · similarity 0.91)
- Direction-Aware Video Demoiréing with Temporal-Guided Bilateral Learning (AAAI 2024 · similarity 0.88)
- DiffRAW: Leveraging Diffusion Model to Generate DSLR-Comparable Perceptual Quality sRGB from Smartphone RAW Images (AAAI 2024 · similarity 0.84)
- UniDemoiré: Towards Universal Image Demoiréing with Data Generation and Synthesis (AAAI 2025 · similarity 0.83)
- MambaSCI: Efficient Mamba-UNet for Quad-Bayer Patterned Video Snapshot Compressive Imaging (NeurIPS 2024 · similarity 0.82)
- Efficient RAW Image Deblurring with Adaptive Frequency Modulation (NeurIPS 2025 · similarity 0.82)
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.
