Research map / Image generation / Super-resolution
Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network
Namhyuk Ahn, Byungkon Kang, Kyung-Ah Sohn
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 global cascading to ResNet baseline (local cascading absent) (ablation) | ResNet baseline · Set14 x4 | PSNR (dB): 28.43 -> 28.45 | Improved |
| add local cascading only to ResNet baseline (ablation) | ResNet baseline · Set14 x4 | PSNR (dB): 28.43 -> 28.42 | Hurt |
| add local cascading on top of global cascading (ablation) | CARN-NL · Set14 x4 | PSNR (dB): 28.45 -> 28.52 | Improved |
| add global cascading on top of local cascading (ablation) | CARN-NG · Set14 x4 | PSNR (dB): 28.42 -> 28.52 | Improved |
| make cascading blocks recursive (shared parameters) (ablation) | CARN residual-E · Set14 x4 | PSNR (dB) | Hurt |
| increase group size in efficient residual block up to 64 (ablation) | CARN · Set14 x4 | PSNR (dB) | Hurt |
| use residual-E blocks (group size 4) and recursive cascading (CARN-M) instead of CARN | CARN · Set14 x4 | PSNR (dB): loss of 0.29 PSNR | Hurt |
| use CARN cascading instead of SelNet at similar operation counts | SelNet · x2 benchmarks | PSNR (dB): +0.11 PSNR | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MemNet — MemNet: A Persistent Memory Network for Image Restoration (ICCV 2017) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Accurate Image Super-Resolution Using Very Deep Convolutional Networks (CVPR 2016 · similarity 0.90)
- Image Super-Resolution Using Deep Convolutional Networks (TPAMI 2016 · similarity 0.90)
- Image Super-Resolution Using Very Deep Residual Channel Attention Networks (ECCV 2018 · similarity 0.90)
- Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks (TPAMI 2018 · similarity 0.90)
- Densely Residual Laplacian Super-Resolution (TPAMI 2020 · similarity 0.90)
- LatticeNet: Towards Lightweight Image Super-resolution with Lattice Block (ECCV 2020 · similarity 0.90)
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.
