Research map / Video / Video segmentation and tracking
Video Demoireing Using Focused-Defocused Dual-Camera System
Dong Xuan, Xiangyuan Sun, Xia Wang, Jian Song, Ya Li, Weixin Li
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 foreground objects to synthetic training images (ablation) | dual-camera demoireing network · DualReal | visual quality | Improved |
| use all four losses instead of subsets (ablation) | demoireing network · DualSynthetic | demoireing quality | Improved |
| add defocused frame as guidance (ablation) | demoireing network · DualReal | demoireing quality | Improved |
| add joint bilateral filter recovery step (ablation) | pipeline · DualReal | tonal consistency and moire in occlusions | Improved |
| add optical-flow alignment of defocused frame (ablation) | pipeline · DualReal | artifacts | Improved |
| use proposed network instead of MMDM, BPN or VDM_PCD networks (ablation) | demoireing network · DualReal | demoireing quality | Improved |
| guide joint bilateral filter with defocused alignment I_A instead of network output I_R (ablation) | JBF · DualReal | detail preservation | Hurt |
| add DualSyntheticVideo to training data (ablation) | demoireing network · DualReal | occlusion region quality | Improved |
| dual-camera method versus video demoireing VDM_PCD | Ours · DualSynthetic | PSNR: 33.38 -> 34.38 | Improved |
| dual-camera method versus best single-camera baseline DMCNN | Ours · DualSyntheticVideo | PSNR: 33.88 -> 39.23 | Improved |
| dual-camera method versus SiamTrans on temporal consistency | Ours · DualSyntheticVideo | t-MSE: 44.46 vs 44.89 | Mixed |
| dual-camera method versus SiamTrans on DualReal t-SSIM | Ours · DualReal | t-SSIM: 0.9119 vs 0.8955 | Mixed |
Closest papers by meaning
- Self-Adaptively Learning to Demoiré from Focused and Defocused Image Pairs (NeurIPS 2020 · similarity 0.90)
- Direction-Aware Video Demoiréing with Temporal-Guided Bilateral Learning (AAAI 2024 · similarity 0.89)
- Learning Image Demoiréing from Unpaired Real Data (AAAI 2024 · similarity 0.86)
- UniDemoiré: Towards Universal Image Demoiréing with Data Generation and Synthesis (AAAI 2025 · similarity 0.86)
- Through the Lens: Benchmarking Deepfake Detectors Against Moiré-Induced Distortions (NeurIPS 2025 · similarity 0.84)
- Dynamic Gaussian Splatting from Defocused and Motion-blurred Monocular Videos (NeurIPS 2025 · similarity 0.84)
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.
