Research map / Image generation / Super-resolution

CNN and transformer SR architectures

Design deep recursive, attention, and transformer architectures for single-image super-resolution.

62 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Super-resolution, keyword cluster “image super · attention · resolution diffusion”

State History Benchmarks Tried Checklist Preprints Who Export

How it got here

Most cited paper of each year

• 2016 · Deeply-Recursive Convolutional Network for Image Super-Resolution (CVPR 2016 · 3,131 citations)
• 2017 · Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (CVPR 2017 · 12,597 citations)
• 2018 · Residual Dense Network for Image Super-Resolution (CVPR 2018 · 4,176 citations)
• 2019 · Feedback Network for Image Super-Resolution (CVPR 2019 · 873 citations)
• 2020 · Deep Unfolding Network for Image Super-Resolution (CVPR 2020 · 653 citations)
• 2021 · Interpreting Super-Resolution Networks With Local Attribution Maps (CVPR 2021 · 346 citations)
• 2022 · Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution (CVPR 2022 · 217 citations)
• 2023 · N-Gram in Swin Transformers for Efficient Lightweight Image Super-Resolution (CVPR 2023 · 222 citations)
• 2024 · Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary (CVPR 2024 · 109 citations)
• 2025 · Exploring Semantic Feature Discrimination for Perceptual Image Super-Resolution and Opinion-Unaware No-Reference Image Quality Assessment (CVPR 2025 · 3 citations)
• 2026 · CD-DPE: Dual-Prompt Expert Network Based on Convolutional Dictionary Feature Decoupling for Multi-Contrast MRI Super-Resolution (AAAI 2026 · 1 citation)

Earliest papers here

• Deeply-Recursive Convolutional Network for Image Super-Resolution (CVPR 2016 · 3,131 citations)
• Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (CVPR 2017 · 12,597 citations)
• Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution (CVPR 2017 · 3,099 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.

What has been tried

56 papers here report 528 measured changes (a component added, removed or swapped, compared with a baseline): helped 76%, no clear effect 6%, hurt 16%, mixed 3%. Papers mostly publish changes that helped, so "helped" is over-represented.

Ablations in recent papers

What reviewers will expect

Datasets and baselines named in the 10 papers of this approach from 2024–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.

Recent preprints

Who publishes on it

Institutions on the most papers of this approach since 2023 (of 23 papers; from OpenAlex and the papers' affiliations).

• ETH Zurich · 3 papers
• Huawei · 3 papers
• University of Electronic Science and Technology of China · 2 papers

Use it

Download BibTeX of 35 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

• Efficient lightweight super-resolution (101 papers)
• Perceptual and real-world SR (85 papers)
• Diffusion-based super-resolution (85 papers)

Elsewhere in the topic

• Real-world super-resolution (72 papers)
• Blind super-resolution (24 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).