Research map / Image generation / Super-resolution
Deep Burst Super-Resolution
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 multiple shifted frames instead of a single image | Deep Burst Super-Resolution · Synthetic data | PSNR: 36.42 -> 39.09 | Helped |
| Increase burst size from 4 to 14 frames (ablation) | Deep Burst Super-Resolution · Synthetic data | PSNR: 37.18 -> 39.09 | Helped |
| Add explicit flow-based alignment (ablation) | Deep Burst Super-Resolution · BurstSR validation set | PSNR: 46.50 -> 47.52 | Helped |
| Add explicit flow-based alignment (ablation) | Deep Burst Super-Resolution · Synthetic data | PSNR: 36.66 -> 38.61 | Helped |
| Replace attention fusion with max pooling (ablation) | Deep Burst Super-Resolution · Synthetic data | PSNR: 38.61 -> 36.24 | Hurt |
| Replace attention fusion with average pooling (ablation) | Deep Burst Super-Resolution · Synthetic data | PSNR: 38.61 -> 35.45 | Hurt |
| Replace attention fusion with concatenation (ablation) | Deep Burst Super-Resolution · Synthetic data | PSNR: 38.61 -> 37.80 | Hurt |
| Replace attention fusion with recursive merging (ablation) | Deep Burst Super-Resolution · Synthetic data | PSNR: 38.61 -> 37.55 | Hurt |
| Use feature residuals instead of only projected frame features in the weight predictor (ablation) | Deep Burst Super-Resolution · Synthetic data | PSNR: 37.46 -> 38.14 | Helped |
| Add base-frame features to residual-based weight prediction (ablation) | Deep Burst Super-Resolution · Synthetic data | PSNR: 38.14 -> 38.41 | Helped |
| Add flow features to residual- and base-feature weight prediction (ablation) | Deep Burst Super-Resolution · Synthetic data | PSNR: 38.41 -> 38.61 | Helped |
| Remove inter-frame sub-pixel shifts (ablation) | Deep Burst Super-Resolution · Synthetic data | PSNR: 37.00 -> 38.61 | Hurt |
Closest papers by meaning
- QMambaBSR: Burst Image Super-Resolution with Query State Space Model (CVPR 2025 · similarity 0.90)
- Burst Image Restoration and Enhancement (CVPR 2022 · similarity 0.89)
- Real-Time Video Super-Resolution With Spatio-Temporal Networks and Motion Compensation (CVPR 2017 · similarity 0.89)
- SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network (AAAI 2024 · similarity 0.87)
- Sequence Matters: Harnessing Video Models in 3D Super-Resolution (AAAI 2025 · similarity 0.86)
- WaveMixSR-V2: Enhancing Super-resolution with Higher Efficiency (Student Abstract) (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.