Research map / Image generation / Super-resolution
Deep Back-ProjectiNetworks for Single Image Super-Resolution
Muhammad Haris, Gregory Shakhnarovich, Norimichi Ukita
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add error feedback (up/down projection units) (ablation) | DBPN-S · Set5 4x | PSNR: 31.06 -> 31.59 | Improved |
| add error feedback (up/down projection units) (ablation) | DBPN-S · Set14 4x | PSNR: 27.95 -> 28.21 | Improved |
| add subtraction/addition error feedback operations (ablation) | D-DBPN · Urban100 4x | PSNR: 26.09 -> 26.38 | Improved |
| add subtraction/addition error feedback operations (ablation) | D-DBPN · Manga109 4x | PSNR: 30.43 -> 30.89 | Improved |
| add dense connection (ablation) | DBPN-L · Set5 4x | PSNR: 31.86 -> 31.99 | Improved |
| add dense connection (ablation) | DBPN-L · Set5 8x | PSNR: 26.63 -> 26.86 | Improved |
| use 8x8 filter instead of 6x6 in projection units (ablation) | D-DBPN · Set5 4x | PSNR: 32.39 -> 32.47 | Improved |
| use 8x8 filter instead of 10x10 in projection units (ablation) | D-DBPN · Set5 4x | PSNR: 32.38 -> 32.47 | Improved |
| use RGB instead of luminance input/output (ablation) | DBPN-L · Set5 4x | PSNR: 31.86 -> 31.88 | No clear effect |
| add residual learning (ablation) | DBPN · Urban100 4x | PSNR: 26.82 -> 26.89 | Improved |
| add recurrent projection units with 3 iterations (ablation) | D-DBPN · Urban100 4x | PSNR: 26.38 -> 26.92 | Improved |
| combine recurrent and residual learning (ablation) | DBPN · Urban100 4x | PSNR: 26.82 -> 27.08 | Improved |
Closest papers by meaning
- Deep Back-Projection Networks for Super-Resolution (CVPR 2018 · similarity 0.98)
- Recurrent Back-Projection Network for Video Super-Resolution (CVPR 2019 · similarity 0.90)
- Image Super-Resolution Using Deep Convolutional Networks (TPAMI 2016 · similarity 0.89)
- Accurate Image Super-Resolution Using Very Deep Convolutional Networks (CVPR 2016 · similarity 0.89)
- Accelerating the Super-Resolution Convolutional Neural Network (ECCV 2016 · similarity 0.89)
- Feedback Network for Image Super-Resolution (CVPR 2019 · similarity 0.89)
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.
