Research map / Video / Video segmentation and tracking
Space-time video super-resolution
Jointly upsamples spatial and temporal resolution using trajectory-aware attention, events and dynamic filters.
33 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2018–2026) · an approach in Video segmentation and tracking, keyword cluster “super resolution · video super · vsr”
State History Benchmarks Tried Checklist Preprints Export
Where it stands
Few recent reports None of the tracked benchmarks has a report from 2025–26.
6 papers in 2023–24 and 8 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic held steady, from 1.4% to 1.5%.
No longer reported by papers here: Vid4 (PSNR, last in 2022); Vid4 (SSIM, last in 2022).
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
- 2018 · Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion Compensation (CVPR 2018 · 636 citations)
- 2019 · Fast Spatio-Temporal Residual Network for Video Super-Resolution (CVPR 2019 · 157 citations)
- 2020 · TDAN: Temporally-Deformable Alignment Network for Video Super-Resolution (CVPR 2020 · 616 citations)
- 2021 · BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond (CVPR 2021 · 615 citations)
- 2022 · Learning Trajectory-Aware Transformer for Video Super-Resolution (CVPR 2022 · 123 citations)
- 2023 · Compression-Aware Video Super-Resolution (CVPR 2023 · 28 citations)
- 2024 · SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network (AAAI 2024 · 14 citations)
- 2025 · BF-STVSR: B-Splines and Fourier---Best Friends for High Fidelity Spatial-Temporal Video Super-Resolution (CVPR 2025 · 6 citations)
- 2026 · Temporal Inconsistency Guidance for Super-resolution Video Quality Assessment (AAAI 2026 · 1 citation)
Earliest papers here
- Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion Compensation (CVPR 2018 · 636 citations)
- Frame-Recurrent Video Super-Resolution (CVPR 2018 · 602 citations)
- Fast Spatio-Temporal Residual Network for Video Super-Resolution (CVPR 2019 · 157 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.
Vid4 · PSNR (higher is better)
8 papers, 2018–2022 · not reported since 2022
| Year | Best so far | Set by |
|---|---|---|
| 2018 | 26.69 | Frame-Recurrent Video Super-Resolution (CVPR 2018 · 602 citations) |
| 2022 | 28.4 | Learning Trajectory-Aware Transformer for Video Super-Resolution (CVPR 2022 · 123 citations) |
Vid4 · SSIM (higher is better)
4 papers, 2018–2022 · not reported since 2022
| Year | Best so far | Set by |
|---|---|---|
| 2018 | 0.822 | Frame-Recurrent Video Super-Resolution (CVPR 2018 · 602 citations) |
| 2021 | 0.84 | Large Motion Video Super-Resolution with Dual Subnet and Multi-Stage Communicated Upsampling (AAAI 2021 · 29 citations) |
What has been tried
28 papers here report 297 measured changes (a component added, removed or swapped, compared with a baseline): helped 81%, no clear effect 3%, hurt 15%, mixed 1%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Add the spatio-temporal filter branch to STAU | Vid4, symmetric ×3.5 and asymmetric ×1.9/×3.5 · PSNR | 27.84 -> 28.03; 30.33 -> 30.58 | Helped | SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network (AAAI 2024 · 14 citations) |
| Add a recurrent hidden state | NFS-syn 4× · RMSE | 0.605 -> 0.599 | Helped | Bilateral Event Mining and Complementary for Event Stream Super-Resolution (CVPR 2024 · 14 citations) |
| Use a pre-trained optical-flow network with both proposed mappers | GoPro-Average and Adobe-Average · PSNR (dB) | 30.03 -> 29.94; 29.81 -> 29.73 | Hurt | BF-STVSR: B-Splines and Fourier---Best Friends for High Fidelity Spatial-Temporal Video Super-Resolution (CVPR 2025 · 6 citations) |
| Add BRC to EMA | GoPro In-Dist. (t=8, s=4) · PSNR (dB) | 32.50 -> 33.13 | Helped | EvEnhancer: Empowering Effectiveness, Efficiency and Generalizability for Continuous Space-Time Video Super-Resolution with Events (CVPR 2025 · 6 citations) |
| add explicit optical-flow alignment | Adobe-Center · PSNR | 30.92 -> 31.79 | Helped | EvSTVSR: Event Guided Space-Time Video Super-Resolution (AAAI 2025 · 5 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
- Adobe240 · 3 of 5 papers
- GoPro · 2 of 5 papers
- BS-ERGB · 2 of 5 papers
Baselines
- VideoINR · 4 of 5 papers
- EDVR · 3 of 5 papers
- BasicVSR · 3 of 5 papers
- TMNet · 3 of 5 papers
- MoTIF · 3 of 5 papers
- LIIF · 2 of 5 papers
- LTE · 2 of 5 papers
- SuperSloMo · 2 of 5 papers
Recent preprints
Loading recent arXiv preprints…
Use it
Download BibTeX of 30 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 video super-resolution (60 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).