Research map / Image generation / Image restoration
Polarized Reflection Removal With Perfect Alignment in the Wild
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use the two-stage polarized reflection-removal framework (ablation) | Reflection removal on M-R · M-R dataset | PSNR (transmission): 32.78 -> 34.62 | Helped |
| Add polarization information to the input (ablation) | Reflection removal on M-R · M-R dataset | PSNR (transmission): 31.92 -> 34.62 | Helped |
| Add PNCC loss (ablation) | Reflection removal on M-R · M-R dataset | PSNR (transmission): 34.42 -> 34.62 | Helped |
| Use 4 polarization inputs rather than 3 (ablation) | Ours · M-R dataset | PSNR (transmission): 33.91 -> 34.62 | Helped |
| Use PNCC instead of exclusion loss | DoubleDIP · DoubleDIP decomposition evaluation | PSNR: 22.43 -> 26.33 | Helped |
| Use PNCC instead of tuned exclusion loss | DoubleDIP · DoubleDIP decomposition evaluation | PSNR: 26.04 -> 26.33 | Helped |
Closest papers by meaning
- PolarFree: Polarization-based Reflection-Free Imaging (CVPR 2025 · similarity 0.92)
- Revisiting Single Image Reflection Removal In the Wild (CVPR 2024 · similarity 0.89)
- Flash-Split: 2D Reflection Removal with Flash Cues and Latent Diffusion Separation (CVPR 2025 · similarity 0.88)
- Learning to Remove Wrinkled Transparent Film with Polarized Prior (CVPR 2024 · similarity 0.86)
- FIRM: Flexible Interactive Reflection ReMoval (AAAI 2025 · similarity 0.86)
- Polarization Guided Mask-Free Shadow Removal (AAAI 2025 · similarity 0.86)
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.