Research map / Image generation / Super-resolution
Benchmarking Burst Super-Resolution for Polarization Images: Noise Dataset and Analysis
Inseung Hwang, Kiseok Choi, Hyunho Ha, Min H. Kim
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 |
|---|---|---|---|
| train MFIR on polarization data instead of using RGB-trained model | MFIR · Real polar dataset DoLP | PSNR: 23.76 -> 22.00 | Hurt |
| train BSRT on polarization data instead of using RGB-trained model | BSRT · Real polar dataset DoLP | PSNR: 23.03 -> 25.17 | Improved |
| train Burstormer on polarization data instead of using RGB-trained model | Burstormer · Real polar dataset DoLP | PSNR: 24.90 -> 25.84 | Improved |
| train FBAnet on polarization data instead of using RGB-trained model | FBAnet · Real polar dataset DoLP | PSNR: 24.28 -> 26.92 | Improved |
| train BurstM on polarization data instead of using RGB-trained model | BurstM · Real polar dataset DoLP | PSNR: 22.78 -> 23.67 | Improved |
| train MFIR on polarization data instead of using RGB-trained model | MFIR · Real polar dataset AoLP | PSNR: 16.67 -> 15.74 | Hurt |
| train BSRT on polarization data instead of using RGB-trained model | BSRT · Real polar dataset AoLP | PSNR: 16.14 -> 17.06 | Improved |
| train Burstormer on polarization data instead of using RGB-trained model | Burstormer · Real polar dataset AoLP | PSNR: 16.95 -> 17.36 | Improved |
| train FBAnet on polarization data instead of using RGB-trained model | FBAnet · Real polar dataset AoLP | PSNR: 16.14 -> 18.14 | Improved |
| train BurstM on polarization data instead of using RGB-trained model | BurstM · Real polar dataset AoLP | PSNR: 16.64 -> 16.32 | Hurt |
| train MFIR on polarization data instead of using RGB-trained model | MFIR · Synthetic polar dataset DoLP | PSNR: 16.79 -> 21.26 | Improved |
| train BSRT on polarization data instead of using RGB-trained model | BSRT · Synthetic polar dataset DoLP | PSNR: 20.70 -> 20.31 | Hurt |
Closest papers by meaning
- PIDSR: Complementary Polarized Image Demosaicing and Super-Resolution (CVPR 2025 · similarity 0.85)
- RGB-to-Polarization Estimation: A New Task and Benchmark Study (NeurIPS 2025 · similarity 0.84)
- QMambaBSR: Burst Image Super-Resolution with Query State Space Model (CVPR 2025 · similarity 0.84)
- PolarFree: Polarization-based Reflection-Free Imaging (CVPR 2025 · similarity 0.83)
- Quality-Improved and Property-Preserved Polarimetric Imaging via Complementarily Fusing (NeurIPS 2024 · similarity 0.83)
- PolarScale: A Physics-Grounded Benchmark for Radiometrically Consistent RGB-to-Stokes Estimation (NeurIPS 2026 · 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.
