Research map / Image generation / Super-resolution
Zoom to Learn, Learn to Zoom
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 real RAW sensor data for training instead of processed 8-bit RGB (ablation) | Ours · SR-RAW 4X | SSIM: 0.589 -> 0.781 | Helped |
| Use real RAW sensor data for training instead of processed 8-bit RGB (ablation) | Ours · SR-RAW 8X | SSIM: 0.638 -> 0.779 | Helped |
| Use real RAW sensor data for training instead of synthetic Bayer data (ablation) | Ours · SR-RAW 4X | PSNR: 23.98 -> 26.88 | Helped |
| Use real RAW sensor data for training instead of synthetic Bayer data (ablation) | Ours · SR-RAW 8X | PSNR: 22.02 -> 24.73 | Helped |
| Use the proposed real-RAW method instead of the strongest baseline | SR-RAW 4X super-resolution · SR-RAW 4X | SSIM: 0.683 -> 0.781 | Helped |
| Use the proposed real-RAW method instead of the strongest baseline | SR-RAW 8X super-resolution · SR-RAW 8X | SSIM: 0.662 -> 0.779 | Helped |
| Add spatial awareness to contextual feature matching with CoBi (ablation) | Training with mildly misaligned SR-RAW pairs · SR-RAW training feature matches | one-to-one feature match percentage: 43.7% to 93.9% | Helped |
| Fine-tune pretrained baselines on SR-RAW rather than use pretrained models without fine-tuning (ablation) | Super-resolution baselines · SR-RAW test set | SSIM: <!\!\pm0.04 | No clear effect |
| Fine-tune pretrained baselines on SR-RAW rather than use pretrained models without fine-tuning (ablation) | Super-resolution baselines · SR-RAW test set | PSNR: <!\!\pm0.05 | No clear effect |
| Fine-tune pretrained baselines on SR-RAW rather than use pretrained models without fine-tuning (ablation) | Super-resolution baselines · SR-RAW test set | LPIPS: <!\!\pm0.025 | No clear effect |
| Fine-tune the pretrained model on a small dataset from the new sensor (ablation) | Ours · iPhoneX-DSLR outdoor data | image quality | Helped |
Closest papers by meaning
- Continuous Optical Zooming: A Benchmark for Arbitrary-Scale Image Super-Resolution in Real World (CVPR 2024 · similarity 0.87)
- ZoomEarth: Active Perception for Ultra-High-Resolution Geospatial Vision-Language Tasks (CVPR 2026 · similarity 0.84)
- ReRAW: RGB-to-RAW Image Reconstruction via Stratified Sampling for Efficient Object Detection on the Edge (CVPR 2025 · similarity 0.83)
- Logarithmic Lenses: Exploring Log RGB Data for Image Classification (CVPR 2024 · similarity 0.83)
- RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes (NeurIPS 2025 · similarity 0.83)
- DORNet: A Degradation Oriented and Regularized Network for Blind Depth Super-Resolution (CVPR 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.