Research map / Image generation / Image restoration
Burst Image Restoration and Enhancement
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 BIPNet instead of MFIR | Burst super-resolution · SyntheticBurst ×4 | PSNR: 41.56 -> 41.93 | Helped |
| Use BIPNet instead of MFIR | Burst super-resolution · BurstSR ×4 | PSNR: 48.33 -> 48.49 | Helped |
| Use BIPNet instead of Karadeniz | Burst low-light enhancement · SID Sony | PSNR: 29.80 -> 32.87 | Helped |
| Use BIPNet instead of MFIR | Burst denoising · Grayscale burst denoising | PSNR (Average): 34.74 -> 36.81 | Helped |
| Use BIPNet instead of MFIR | Burst denoising · Color burst denoising | PSNR (Average): 37.40 -> 38.74 | Helped |
| Add FPM to the baseline (ablation) | BIPNet · SyntheticBurst ×4 ablation | PSNR: 36.38 -> 36.54 | Helped |
| Add DAM (ablation) | BIPNet · SyntheticBurst ×4 ablation | PSNR: 36.54 -> 38.39 | Helped |
| Add RAF (ablation) | BIPNet · SyntheticBurst ×4 ablation | PSNR: 38.39 -> 39.10 | Helped |
| Add PBFF (ablation) | BIPNet · SyntheticBurst ×4 ablation | PSNR: 39.10 -> 39.64 | Helped |
| Add MSF (ablation) | BIPNet · SyntheticBurst ×4 ablation | PSNR: 39.64 -> 40.35 | Helped |
| Add AGU (ablation) | BIPNet · SyntheticBurst ×4 ablation | PSNR: 40.35 -> 41.25 | Helped |
| Add EBFA (ablation) | BIPNet · SyntheticBurst ×4 ablation | PSNR: 41.25 -> 41.55 | Helped |
Closest papers by meaning
- Burstormer: Burst Image Restoration and Enhancement Transformer (CVPR 2023 · similarity 0.93)
- QMambaBSR: Burst Image Super-Resolution with Query State Space Model (CVPR 2025 · similarity 0.88)
- Neural Spline Fields for Burst Image Fusion and Layer Separation (CVPR 2024 · similarity 0.84)
- Event-Enhanced Blurry Video Super-Resolution (AAAI 2025 · similarity 0.83)
- FMA-Net: Flow-Guided Dynamic Filtering and Iterative Feature Refinement with Multi-Attention for Joint Video Super-Resolution and Deblurring (CVPR 2024 · similarity 0.83)
- Sequence Matters: Harnessing Video Models in 3D Super-Resolution (AAAI 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.