Research map / Video / Video segmentation and tracking
Real-world video super-resolution
Restores real-world low-resolution video with GAN detail synthesis, alignment and artifact mitigation.
60 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2017–2026) · an approach in Video segmentation and tracking, keyword cluster “super resolution · video super · vsr”
State History Benchmarks Tried Checklist Preprints Who Export
Where it stands
Few recent reports The tracked benchmarks have at most one report from 2025–26 that could beat the old record, too few to say whether they are still moving.
14 papers in 2023–24 and 29 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic grew, from 3.2% to 5.4%.
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
- 2017 · Real-Time Video Super-Resolution With Spatio-Temporal Networks and Motion Compensation (CVPR 2017 · 800 citations)
- 2019 · Recurrent Back-Projection Network for Video Super-Resolution (CVPR 2019 · 577 citations)
- 2020 · Video Super-Resolution With Temporal Group Attention (CVPR 2020 · 211 citations)
- 2021 · Understanding Deformable Alignment in Video Super-Resolution (AAAI 2021 · 159 citations)
- 2022 · BasicVSR++: Improving Video Super-Resolution With Enhanced Propagation and Alignment (CVPR 2022 · 586 citations)
- 2023 · Learning Spatial-Temporal Implicit Neural Representations for Event-Guided Video Super-Resolution (CVPR 2023 · 53 citations)
- 2024 · Video Super-Resolution Transformer with Masked Inter&Intra-Frame Attention (CVPR 2024 · 36 citations)
- 2025 · Event-based Video Super-Resolution via State Space Models (CVPR 2025 · 27 citations)
- 2026 · Ultralight Polarity-Split Neuromorphic SNN for Event-Stream Super-Resolution (AAAI 2026 · 4 citations)
Earliest papers here
- Real-Time Video Super-Resolution With Spatio-Temporal Networks and Motion Compensation (CVPR 2017 · 800 citations)
- Privacy-Preserving Human Activity Recognition from Extreme Low Resolution (AAAI 2017 · 157 citations)
- Building an End-to-End Spatial-Temporal Convolutional Network for Video Super-Resolution (AAAI 2017 · 53 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.
REDS4 · PSNR (higher is better)
5 papers, 2021–2025 · one report since 2024, not better
| Year | Best so far | Set by |
|---|---|---|
| 2021 | 30.24 | Understanding Deformable Alignment in Video Super-Resolution (AAAI 2021 · 159 citations) |
| 2022 | 32.72 | Rethinking Alignment in Video Super-Resolution Transformers (NeurIPS 2022 · 34 citations) |
VideoLQ · NIQE (lower is better)
4 papers, 2022–2025 · one report since 2024, not better
| Year | Best so far | Set by |
|---|---|---|
| 2022 | 2.569 | Investigating Tradeoffs in Real-World Video Super-Resolution (CVPR 2022 · 120 citations) |
What has been tried
39 papers here report 431 measured changes (a component added, removed or swapped, compared with a baseline): helped 78%, no clear effect 5%, hurt 15%, 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 |
|---|---|---|---|---|
| replace multi-frame self-attention with intra/inter-frame attention | REDS4 · PSNR | 31.03 -> 31.12 | Helped | Video Super-Resolution Transformer with Masked Inter&Intra-Frame Attention (CVPR 2024 · 36 citations) |
| add positional encoding on decimal offsets and window indices | Sintel · PSNR | 30.43 -> 30.71 | Helped | Enhancing Video Super-Resolution via Implicit Resampling-based Alignment (CVPR 2024 · 34 citations) |
| Add the iMamba block to the core modules | CED ×2 · PSNR | 40.17 -> 41.14 | Helped | Event-based Video Super-Resolution via State Space Models (CVPR 2025 · 27 citations) |
| Add SFA to the UNet | REDS4 · PSNR | 28.56 -> 28.93 | Helped | Learning Spatial Adaptation and Temporal Coherence in Diffusion Models for Video Super-Resolution (CVPR 2024 · 27 citations) |
| Add temporal attention | REDS4 · LPIPS | 0.2031 -> 0.2029 | No clear effect | VideoGigaGAN: Towards Detail-rich Video Super-Resolution (CVPR 2025 · 22 citations) |
| replace conventional dynamic filtering with FGDF | REDS4 · PSNR (dB) | 27.86 -> 28.83 | Helped | FMA-Net: Flow-Guided Dynamic Filtering and Iterative Feature Refinement with Multi-Attention for Joint Video Super-Resolution and Deblurring (CVPR 2024 · 22 citations) |
| Add CHM to the no-CHM baseline | GoPro · PSNR | 31.84 -> 32.26 | Helped | Learning Truncated Causal History Model for Video Restoration (NeurIPS 2024 · 16 citations) |
| add GPS | YTVIS-19 · PSNR | 36.75 -> 36.84 | Helped | Semantic Lens: Instance-Centric Semantic Alignment for Video Super-resolution (AAAI 2024 · 14 citations) |
| use radiance demodulation instead of direct image super-resolution | Bistro · PSNR (dB) | 24.78 -> 25.45 | Helped | Neural Super-Resolution for Real-time Rendering with Radiance Demodulation (CVPR 2024 · 11 citations) |
| Add DFM instead of using ResBlock in the encoder | Rendering test datasets (average) · PSNR | 29.17 -> 29.37 | Helped | Efficient Video Super-Resolution for Real-time Rendering with Decoupled G-buffer Guidance (CVPR 2025 · 10 citations) |
| add inter-frame events to intra-frame event processing | GoPro 4× BVSR · PSNR | 31.32 -> 32.51 | Helped | Event-Enhanced Blurry Video Super-Resolution (AAAI 2025 · 8 citations) |
| Add independently sampled noise | VideoLQ · NIQE | 3.936 -> 3.643 | Helped | NegVSR: Augmenting Negatives for Generalized Noise Modeling in Real-world Video Super-Resolution (AAAI 2024 · 7 citations) |
What reviewers will expect
Datasets and baselines named in the 10 papers of this approach from 2025–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.
Datasets
- REDS · 3 of 10 papers
- UDM10 · 3 of 10 papers
- SPMCS · 2 of 10 papers
- VideoLQ · 2 of 10 papers
Baselines
- BasicVSR++ · 4 of 10 papers
- EvTexture · 3 of 10 papers
- MIA-VSR · 2 of 10 papers
- EGVSR · 2 of 10 papers
- TDAN · 2 of 10 papers
- EDVR · 2 of 10 papers
- VRT · 2 of 10 papers
- TTVSR · 2 of 10 papers
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 43 papers; from OpenAlex and the papers' affiliations).
- University of Science and Technology of China · 5 papers
- National University of Singapore · 3 papers
- Tsinghua University · 2 papers
- Chinese Academy of Sciences · 2 papers
- Nanyang Technological University · 2 papers
- Huawei · 2 papers
Use it
Download BibTeX of 38 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
- Space-time video super-resolution (33 papers)
Elsewhere in the topic
- Self-supervised video representation learning (167 papers)
- Video restoration with temporal priors (159 papers)
- Layered video decomposition and dynamics (140 papers)
- Stochastic video prediction (125 papers)
- Physics-inspired motion prediction (113 papers)
- Sign language and physiological video analysis (99 papers)
- Weakly supervised video anomaly detection (99 papers)
- Spatio-temporal predictive modeling (91 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).