Research map / Image generation / Super-resolution
Multigrid Backprojection Super–Resolution and Deep Filter Visualization
Read the paperCheck 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 MGBP super-resolution instead of EDSR | Our · Set14 2× | PSNR: 33.27 vs 33.92 | Hurt |
| Use MGBP super-resolution instead of EDSR | Our · BSDS100 2× | PSNR: 31.99 vs 32.32 | Hurt |
| Use MGBP super-resolution instead of EDSR | Our · Urban100 2× | PSNR: 31.37 vs 32.93 | Hurt |
| Use MGBP super-resolution instead of EDSR | Our · Manga109 2× | PSNR: 37.92 vs 39.10 | Hurt |
| Use MGBP super-resolution instead of D-DBPN | Our · Set14 4× | PSNR: 28.43 vs 28.82 | Hurt |
| Use MGBP super-resolution instead of D-DBPN | Our · BSDS100 4× | PSNR: 27.42 vs 27.72 | Hurt |
| Use MGBP super-resolution instead of EDSR | Our · Urban100 4× | PSNR: 25.70 vs 26.64 | Hurt |
| Use MGBP super-resolution instead of D-DBPN | Our · Manga109 4× | PSNR: 30.07 vs 31.18 | Hurt |
| Use MGBP super-resolution instead of D-DBPN | Our · Set14 8× | PSNR: 24.82 vs 25.13 | Hurt |
| Use MGBP super-resolution instead of D-DBPN | Our · BSDS100 8× | PSNR: 24.67 vs 24.88 | Hurt |
| Use MGBP super-resolution instead of D-DBPN | Our · Urban100 8× | PSNR: 22.21 vs 22.83 | Hurt |
| Use MGBP super-resolution instead of D-DBPN | Our · Manga109 8× | PSNR: 24.12 vs 25.30 | Hurt |
Closest papers by meaning
- Block-Based Multi-Scale Image Rescaling (AAAI 2025 · similarity 0.85)
- ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Models (ICLR 2024 · similarity 0.85)
- UPS: Unified Projection Sharing for Lightweight Single-Image Super-resolution and Beyond (NeurIPS 2024 · similarity 0.85)
- ResDiff: Combining CNN and Diffusion Model for Image Super-resolution (AAAI 2024 · similarity 0.85)
- Decompositional Neural Scene Reconstruction with Generative Diffusion Prior (CVPR 2025 · similarity 0.85)
- DEALing with Image Reconstruction: Deep Attentive Least Squares (ICML 2025 · similarity 0.84)
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.
