Research map / Image generation / Super-resolution
Blind super-resolution
Estimate or represent unknown degradation kernels for blind super-resolution.
24 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2019–2026) · an approach in Super-resolution, keyword cluster “lr · hr · degradation”
State History Benchmarks Tried Checklist Preprints Export
Where it stands
Still moving The best reported result is still improving on 1 of 1 tracked benchmark.
6 papers in 2023–24 and 3 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 5.1% to 1.8%.
Open questions the data points to
- DIV2KRK ×2 (PSNR): best went from 32.75 (up to 2024) to 33.31 in 2025 — Unsupervised Degradation Representation Aware Transform for Real-World Blind Image Super-Resolution (AAAI 2025 · 2 citations)
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2019 · Blind Super-Resolution With Iterative Kernel Correction (CVPR 2019 · 591 citations)
- 2020 · Unfolding the Alternating Optimization for Blind Super Resolution (NeurIPS 2020 · 146 citations)
- 2021 · Unsupervised Degradation Representation Learning for Blind Super-Resolution (CVPR 2021 · 418 citations)
- 2022 · Deep Constrained Least Squares for Blind Image Super-Resolution (CVPR 2022 · 145 citations)
- 2023 · Better "CMOS" Produces Clearer Images: Learning Space-Variant Blur Estimation for Blind Image Super-Resolution (CVPR 2023 · 20 citations)
- 2024 · A Dynamic Kernel Prior Model for Unsupervised Blind Image Super-Resolution (CVPR 2024 · 37 citations)
- 2025 · DORNet: A Degradation Oriented and Regularized Network for Blind Depth Super-Resolution (CVPR 2025 · 9 citations)
- 2026 · KernelFusion: Zero-Shot Blind Super-Resolution via Patch Diffusion (ICLR 2026)
Earliest papers here
- Blind Super-Resolution With Iterative Kernel Correction (CVPR 2019 · 591 citations)
- Deep Plug-And-Play Super-Resolution for Arbitrary Blur Kernels (CVPR 2019 · 418 citations)
- Blind Super-Resolution Kernel Estimation using an Internal-GAN (NeurIPS 2019 · 215 citations)
Benchmark records
The best number each year that beat every earlier one, among papers of this approach reporting their own method. Numbers are extracted by AI from each paper's text; check the paper before citing.
DIV2KRK ×2 · PSNR (higher is better)
4 papers, 2020–2025 · still improving
| Year | Best so far | Set by |
|---|---|---|
| 2020 | 32.56 | Unfolding the Alternating Optimization for Blind Super Resolution (NeurIPS 2020 · 146 citations) |
| 2022 | 32.75 | Deep Constrained Least Squares for Blind Image Super-Resolution (CVPR 2022 · 145 citations) |
| 2025 | 33.31 | Unsupervised Degradation Representation Aware Transform for Real-World Blind Image Super-Resolution (AAAI 2025 · 2 citations) |
What has been tried
22 papers here report 213 measured changes (a component added, removed or swapped, compared with a baseline): helped 72%, no clear effect 5%, hurt 21%, mixed 2%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Remove the RKS module | Gaussian kernels, Set14 x4 · image PSNR | 25.98 -> 18.77 | Hurt | A Dynamic Kernel Prior Model for Unsupervised Blind Image Super-Resolution (CVPR 2024 · 37 citations) |
| Add degradation prior to the no-prior model | Set5, ×4, kernel width 1.2 · PSNR | 32.074 -> 32.372 | Helped | CDFormer: When Degradation Prediction Embraces Diffusion Model for Blind Image Super-Resolution (CVPR 2024 · 25 citations) |
| Add degradation learning (DL) to the baseline | RGB-D-D · RMSE | Helped | DORNet: A Degradation Oriented and Regularized Network for Blind Depth Super-Resolution (CVPR 2025 · 9 citations) | |
| Add GDA blocks | DIV2KRK, ×2 · PSNR | 32.69 -> 33.31 | Helped | Unsupervised Degradation Representation Aware Transform for Real-World Blind Image Super-Resolution (AAAI 2025 · 2 citations) |
What reviewers will expect
Datasets and baselines named in the 5 papers of this approach from 2024–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.
Datasets
- DIV2K · 3 of 5 papers
- Set5 · 3 of 5 papers
- Set14 · 3 of 5 papers
- BSD100 · 3 of 5 papers
- Urban100 · 3 of 5 papers
- Flickr2K · 2 of 5 papers
- Manga109 · 2 of 5 papers
Baselines
- DCLS · 3 of 5 papers
- DASR · 3 of 5 papers
Recent preprints
Loading recent arXiv preprints…
Use it
Download BibTeX of 22 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Real-world super-resolution (72 papers)
Elsewhere in the topic
- Efficient lightweight super-resolution (101 papers)
- Perceptual and real-world SR (85 papers)
- Diffusion-based super-resolution (85 papers)
- CNN and transformer SR architectures (62 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).