Research map / Image generation / Super-resolution
Blind Super-Resolution Kernel Estimation using an Internal-GAN
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 KernelGAN-estimated rather than Michaeli & Irani-estimated kernels with ZSSR | ZSSR · DIV2KRK, ×2 | PSNR (dB): +1.1dB | Helped |
| Use KernelGAN-estimated rather than Michaeli & Irani-estimated kernels with ZSSR | ZSSR · DIV2KRK, ×4 | PSNR (dB): +0.47dB | Helped |
| Use KernelGAN-estimated rather than Michaeli & Irani-estimated kernels with SRMD | SRMD · DIV2KRK, ×2 | PSNR (dB): +1dB | Helped |
| Use KernelGAN-estimated rather than Michaeli & Irani-estimated kernels with SRMD | SRMD · DIV2KRK, ×4 | PSNR (dB): +0.73dB | Helped |
| Use KernelGAN-estimated rather than Michaeli & Irani-estimated kernels with ZSSR | ZSSR · DIV2KRK, ×2 | PSNR (dB): +4dB | Helped |
| Use KernelGAN-estimated rather than Michaeli & Irani-estimated kernels with ZSSR | ZSSR · DIV2KRK, ×4 | PSNR (dB): +2.3dB | Helped |
| Replace the single-layer linear generator with a deep linear generator (ablation) | KernelGAN · DIV2KRK, ×2 | PSNR (dB): 3.8dB | Helped |
| Replace the single-layer linear generator with a deep linear generator (ablation) | KernelGAN · DIV2KRK, ×4 | PSNR (dB): 1.6dB | Helped |
| Use KernelGAN-estimated rather than Michaeli & Irani-estimated kernels with SRMD | SRMD · DIV2KRK, ×4 | SSIM | Helped |
Closest papers by meaning
- Learning Controllable Degradation for Real-World Super-Resolution via Constrained Flows (ICML 2023 · similarity 0.84)
- Unfolding the Alternating Optimization for Blind Super Resolution (NeurIPS 2020 · similarity 0.83)
- Deep Constrained Least Squares for Blind Image Super-Resolution (CVPR 2022 · similarity 0.83)
- Deep Generative Model based Rate-Distortion for Image Downscaling Assessment (CVPR 2024 · similarity 0.81)
- Unsupervised Degradation Representation Aware Transform for Real-World Blind Image Super-Resolution (AAAI 2025 · similarity 0.80)
- Navigating Beyond Dropout: An Intriguing Solution towards Generalizable Image Super Resolution (CVPR 2024 · similarity 0.79)
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.