Research map / Image generation / Super-resolution
Fast Bayesian Uncertainty Estimation and Reduction of Batch Normalized Single Image Super-Resolution Network
Aupendu Kar, Prabir Kumar Biswas
Check 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 |
|---|---|---|---|
| Generate MC samples in a single forward pass rather than repeated MCBN inference | Bayesian VDSR · Set14 face, 5–15 MC samples | relative inference time: 14.28 vs 1.0; 33.48 vs 1.97; 52.67 vs 2.96 | Improved |
| Apply uncertainty reduction (ablation) | BayesianVDSR · BSD100 adversarial attacks, levels 1–16, ×2/×3/×4 | PSNR: 31.16/ 28.36/ 27.03 -> 31.55/ 28.63/ 27.16; 18.04/ 18.37/ 18.82 -> 24.78/ 24.64/ 23.94 | Improved |
| Apply uncertainty reduction (ablation) | BayesianVDSR · BSD100, no attack, ×2/×3/×4 | PSNR: 32.02/ 28.95/ 27.43 -> 31.94/ 28.87/ 27.32 | Hurt |
| Apply uncertainty reduction (ablation) | BayesianVDSR · Set5, Gaussian noise level 5, ×2/×3/×4 | PSNR: 33.44/ 31.28/ 29.70 -> 34.08/ 31.69/ 29.78 | Mixed |
| Apply uncertainty reduction (ablation) | BayesianVDSR · Set5, Gaussian noise levels 10 and 15, ×2/×3/×4 | PSNR: 29.32/ 28.06/ 27.18 -> 31.68/ 29.73/ 28.17; 26.43/ 25.61/ 25.04 -> 29.65/ 28.31/ 27.12 | Improved |
| Apply uncertainty reduction (ablation) | BayesianVDSR · Noisy LR images with Poisson or Speckle noise, ×2/×3/×4 | PSNR: 29.16/ 28.04/ 27.10 -> 31.28/ 29.49/ 28.10; 27.80/ 26.83/ 26.22 -> 29.73/ 28.58/ 27.45 | Improved |
| Increase the number of MC samples | Bayesian VDSR · BSD100 | PSNR | Improved |
Closest papers by meaning
- Uncertainty-Aware GAN for Single Image Super Resolution (AAAI 2024 · similarity 0.90)
- Uncertainty-guided Perturbation for Image Super-Resolution Diffusion Model (CVPR 2025 · similarity 0.88)
- ResDiff: Combining CNN and Diffusion Model for Image Super-resolution (AAAI 2024 · similarity 0.87)
- BUFF: Bayesian Uncertainty Guided Diffusion Probabilistic Model for Single Image Super-Resolution (AAAI 2025 · similarity 0.87)
- Universal Robustness via Median Randomized Smoothing for Real-World Super-Resolution (CVPR 2024 · similarity 0.86)
- Noise-Free Optimization in Early Training Steps for Image Super-resolution (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.
