Research map / Image generation / Super-resolution
Unified Dynamic Convolutional Network for Super-Resolution With Variational Degradations
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 |
|---|---|---|---|
| Replace standard convolutions with dynamic convolution blocks (ablation) | UDVD · Set5, ×3, kernel width 1.3, noise 15 | PSNR: 29.45 -> 29.56 | Helped |
| Use upsampling dynamic convolution followed by dynamic convolution blocks (ablation) | UDVD · Set5, ×3, kernel width 1.3, noise 15 | PSNR: 29.56 -> 29.61 | Helped |
| Add multistage loss at intermediate dynamic-block outputs (ablation) | UDVD_UDD · Set5, ×3, kernel width 1.3, noise 15 | PSNR: 29.58 -> 29.67 | Helped |
| Add multistage loss at intermediate dynamic-block outputs (ablation) | UDVD_UDD · Set5, ×3, kernel width 1.3, noise 15 | SSIM: 0.8385 -> 0.8410 | Helped |
| Use dynamic convolution for varied blur and noise degradations | UDVD versus SRMD · Set5, kernel width 0.2, noise 15, ×2 | PSNR: 32.76 -> 32.96 | Helped |
| Use dynamic convolution to handle spatially varying blur and noise | UDVD versus SRMD · Set5, spatially varying kernel width [0.2, 2], noise [5, 50], ×2 | PSNR: 28.53 -> 29.37 | Helped |
| Use one unified model for bicubic and noisy degradations | UDVD* versus RDN · Set5, fixed DN, ×3 | PSNR: 28.47 -> 28.52 | Helped |
| Use UDVD instead of SFTMD | Noise-free super-resolution · Set5, kernel width 0.2, ×2 | PSNR: 38.00 -> 38.01 | No clear effect |
Closest papers by meaning
- Learning a Single Convolutional Super-Resolution Network for Multiple Degradations (CVPR 2018 · similarity 0.92)
- Accurate Image Super-Resolution Using Very Deep Convolutional Networks (CVPR 2016 · similarity 0.89)
- Unsupervised Degradation Representation Learning for Blind Super-Resolution (CVPR 2021 · similarity 0.89)
- End-to-End Learning for Joint Image Demosaicing, Denoising and Super-Resolution (CVPR 2021 · similarity 0.88)
- SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network (AAAI 2024 · similarity 0.88)
- ResDiff: Combining CNN and Diffusion Model for Image Super-resolution (AAAI 2024 · 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.