Research map / Image generation / Super-resolution
Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution
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 |
|---|---|---|---|
| add residual learning and image reconstruction branch (ablation) | LapSRN · Set5 and Set14, 4× | PSNR: 30.58 -> 31.28; 27.61 -> 28.04 | Helped |
| add the Laplacian pyramid structure (ablation) | LapSRN · Set5 and Set14, 4× | PSNR: 30.58 -> 31.28; 27.61 -> 28.04 | Helped |
| use robust Charbonnier loss instead of L2 loss (ablation) | LapSRN · Set5 and Set14, 4× | PSNR: 30.93 -> 31.28; 27.86 -> 28.04 | Helped |
| increase network depth from 5 to 15 at each level (ablation) | LapSRN · Set5 and Set14, 4× | PSNR: 31.28 -> 31.45; 28.04 -> 28.16 | Helped |
| increase network depth from 5 to 15 at each level (ablation) | LapSRN · Set5 and Set14, 4× | runtime (seconds): 0.044 -> 0.077; 0.042 -> 0.071 | Hurt |
| use the general 8× model's intermediate outputs rather than scale-specific models | LapSRN · 2× and 4× super-resolution | PSNR | Hurt |
Closest papers by meaning
- Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network (CVPR 2016 · similarity 0.88)
- Joint Sub-bands Learning with Clique Structures for Wavelet Domain Super-Resolution (NeurIPS 2018 · similarity 0.88)
- Accurate Image Super-Resolution Using Very Deep Convolutional Networks (CVPR 2016 · similarity 0.88)
- LaMAR: Laplacian Pyramid for Multimodal Adaptive Super Resolution (Student Abstract) (AAAI 2024 · similarity 0.88)
- ResDiff: Combining CNN and Diffusion Model for Image Super-resolution (AAAI 2024 · similarity 0.87)
- SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network (AAAI 2024 · similarity 0.86)
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.