Research map / Image generation / Super-resolution
Uncertainty-Driven Loss for Single Image Super-Resolution
Qian Ning, Weisheng Dong, Xin Li, Jinjian Wu, Guangming Shi
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 |
|---|---|---|---|
| replace L1 loss with uncertainty-estimation loss LEU alone (ablation) | EDSR-S x4 · Urban100 | PSNR (dB): 24.71 -> 24.21 | Hurt |
| replace L1 loss with LESU alone (ablation) | EDSR-S x4 · Urban100 | PSNR (dB): 24.71 -> 24.27 | Hurt |
| add uncertainty-driven loss LUDL stage with LESU pretraining (full method) | EDSR-S x4 · Urban100 | PSNR (dB): 25.25 -> 25.54 | Improved |
| use LESU (Jeffrey's prior sparsity) instead of LEU at step 1 (ablation) | LUDL EDSR-S x4 · Urban100 | PSNR (dB): 25.49 -> 25.54 | Improved |
| weight loss by uncertainty instead of error map (ablation) | EDSR-S x4 · Urban100 | PSNR (dB): 25.40 -> 25.54 | Improved |
| weight loss by uncertainty instead of HR gradient map (ablation) | EDSR-S x4 · Urban100 | PSNR (dB): 25.42 -> 25.54 | Improved |
| use log scaling instead of linear scaling for uncertainty weights (ablation) | LUDL EDSR-S x4 · Urban100 | PSNR (dB): 25.54 -> 25.57 | No clear effect |
| use exp(s) instead of linear scaling (ablation) | LUDL EDSR-S x4 · Urban100 | PSNR (dB): 25.54 -> 25.53 | No clear effect |
| use LUDL instead of GRAM | EDSR-S x4 · Urban100 | PSNR (dB): 24.81 -> 25.54 | Improved |
| use LUDL instead of GRAM | DPDNN x4 · Urban100 | PSNR (dB): 25.63 -> 26.09 | Improved |
| apply GRAM instead of original loss | EDSR-S x4 · Urban100 | PSNR (dB): 25.25 -> 24.81 | Hurt |
| apply LUDL under blur-downsampling degradation | EDSR-S x4 · Urban100 | PSNR (dB): 25.77 -> 25.95 | Improved |
Closest papers by meaning
- Uncertainty-Aware GAN for Single Image Super Resolution (AAAI 2024 · similarity 0.91)
- Adaptive Importance Learning for Improving Lightweight Image Super-Resolution Network (IJCV 2019 · similarity 0.89)
- Perception-Oriented Single Image Super-Resolution Using Optimal Objective Estimation (CVPR 2023 · similarity 0.89)
- Fast Bayesian Uncertainty Estimation and Reduction of Batch Normalized Single Image Super-Resolution Network (CVPR 2021 · similarity 0.89)
- Uncertainty-guided Perturbation for Image Super-Resolution Diffusion Model (CVPR 2025 · similarity 0.88)
- Noise-Free Optimization in Early Training Steps for Image Super-resolution (AAAI 2024 · similarity 0.87)
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.
