Research map / Image generation / Super-resolution
Deep Back-Projection Networks for Super-Resolution
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 D-DBPN instead of EDSR | single-image super-resolution · Set5 8× | PSNR: 26.97 -> 27.21 | Helped |
| Use D-DBPN instead of EDSR | single-image super-resolution · Manga109 8× | PSNR: 24.89^* -> 25.50^* | Helped |
| Use D-DBPN instead of EDSR | single-image super-resolution · Urban100 8× | PSNR: 23.12^* -> 23.25^* | Helped |
| Use D-DBPN instead of EDSR | single-image super-resolution · Urban100 4× | PSNR: 27.30^* -> 27.08^* | Hurt |
| Use D-DBPN instead of EDSR | single-image super-resolution · Set5 2× | PSNR: 38.11 -> 38.09 | No clear effect |
| Use D-DBPN instead of EDSR | single-image super-resolution · Set5 4× | PSNR: 32.46 -> 32.47 | Helped |
| Add dense connections to DBPN-L (ablation) | DBPN-L · Set5 4× | PSNR: 31.86 -> 31.99 | Helped |
| Add dense connections to DBPN-L (ablation) | DBPN-L · Set14 4× | PSNR: 28.47 -> 28.52 | Helped |
| Add dense connections to DBPN-L (ablation) | DBPN-L · Set5 8× | PSNR: 26.63 -> 26.86 | Helped |
| Add dense connections to DBPN-L (ablation) | DBPN-L · Set14 8× | PSNR: 24.73 -> 24.92 | Helped |
| Increase DBPN depth from M (T=4) to L (T=6) (ablation) | DBPN · Set5 4× | PSNR: 31.74 -> 31.86 | Helped |
| Increase DBPN depth from M (T=4) to L (T=6) (ablation) | DBPN · Set5 8× | PSNR: 0.04 dB | No clear effect |
Closest papers by meaning
- Recurrent Back-Projection Network for Video Super-Resolution (CVPR 2019 · similarity 0.90)
- Accurate Image Super-Resolution Using Very Deep Convolutional Networks (CVPR 2016 · similarity 0.89)
- Feedback Network for Image Super-Resolution (CVPR 2019 · similarity 0.89)
- Multigrid Backprojection Super–Resolution and Deep Filter Visualization (AAAI 2019 · similarity 0.89)
- Image Super-Resolution via Dual-State Recurrent Networks (CVPR 2018 · similarity 0.88)
- Closed-Loop Matters: Dual Regression Networks for Single Image Super-Resolution (CVPR 2020 · similarity 0.88)
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.