Research map / Video / Video segmentation and tracking
Spike and neuromorphic deblurring
Removes motion blur and noise using spike streams and neuromorphic event data.
57 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Video segmentation and tracking, keyword cluster “interpolation · flow · event”
State History Tried Checklist Preprints Who Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
23 papers in 2023–24 and 15 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 5.2% to 2.8%.
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
- 2016 · Amplitude Modulated Video Camera - Light Separation in Dynamic Scenes (CVPR 2016 · 6 citations)
- 2017 · Deep Video Deblurring for Hand-Held Cameras (CVPR 2017 · 607 citations)
- 2018 · Learning to Extract a Video Sequence From a Single Motion-Blurred Image (CVPR 2018 · 125 citations)
- 2019 · Bringing Alive Blurred Moments (CVPR 2019 · 67 citations)
- 2020 · Joint Filtering of Intensity Images and Neuromorphic Events for High-Resolution Noise-Robust Imaging (CVPR 2020 · 102 citations)
- 2021 · Learning Temporal Consistency for Low Light Video Enhancement From Single Images (CVPR 2021 · 159 citations)
- 2022 · Context-Aware Video Reconstruction for Rolling Shutter Cameras (CVPR 2022 · 27 citations)
- 2023 · Low-Light Video Enhancement with Synthetic Event Guidance (AAAI 2023 · 36 citations)
- 2024 · DS-NeRV: Implicit Neural Video Representation with Decomposed Static and Dynamic Codes (CVPR 2024 · 23 citations)
- 2025 · Exploring More from Multiple Gait Modalities for Human Identification (AAAI 2025 · 21 citations)
- 2026 · Continuous Exposure-Time Modeling for Realistic Atmospheric Turbulence Synthesis (CVPR 2026 · 0 citations)
Earliest papers here
- Amplitude Modulated Video Camera - Light Separation in Dynamic Scenes (CVPR 2016 · 6 citations)
- Deep Video Deblurring for Hand-Held Cameras (CVPR 2017 · 607 citations)
- Video Acceleration Magnification (CVPR 2017 · 94 citations)
What has been tried
43 papers here report 460 measured changes (a component added, removed or swapped, compared with a baseline): helped 78%, no clear effect 4%, hurt 17%, 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 |
|---|---|---|---|---|
| increase dynamic-code length | Jockey · PSNR | For static length 30: 28.68 -> 30.87 -> 32.16 -> 32.56 | Helped | DS-NeRV: Implicit Neural Video Representation with Decomposed Static and Dynamic Codes (CVPR 2024 · 23 citations) |
| Add common-concern map m_co while retaining m_di | SUSTech1K · R-1 | 86.5 -> 87.4 | Helped | Exploring More from Multiple Gait Modalities for Human Identification (AAAI 2025 · 21 citations) |
| Add the proposed flow network instead of SPyNet | DeepHDRVideo dynamic scenes · PSNRT | 44.82 -> 45.10 | Helped | HDRFlow: Real-Time HDR Video Reconstruction with Large Motions (CVPR 2024 · 17 citations) |
| add instance-specific optimization | Cardiac · PSNR | 33.57 ± 0.275 -> 33.59 ± 0.268 | Helped | Data-Efficient Unsupervised Interpolation Without Any Intermediate Frame for 4D Medical Images (CVPR 2024 · 14 citations) |
| Add MEDM to the baseline | MMD test · Accuracy | 0.857519 -> 0.858176 | Helped | Effective Video Mirror Detection with Inconsistent Motion Cues (CVPR 2024 · 12 citations) |
| add InterF, IntraF, and scene loss | PHM Δt = 10 · AEPE | 0.986 -> 0.640 | Helped | Optical Flow for Spike Camera with Hierarchical Spatial-Temporal Spike Fusion (AAAI 2024 · 9 citations) |
| Add automatic keypoint selection | REDS · MSE | 0.107 ± 0.001 -> 0.103 ± 0.001 | Helped | DeblurSR: Event-Based Motion Deblurring under the Spiking Representation (AAAI 2024 · 8 citations) |
| add event streams | SynHeavy25 · PSNR | 31.85 -> 33.94 | Helped | Neuromorphic Event Signal-Driven Network for Video De-raining (AAAI 2024 · 7 citations) |
| use frame bunches instead of a single Is and Im | Synthetic data · PSNR | 19.95 -> 24.06 | Helped | Towards HDR and HFR Video from Rolling-Mixed-Bit Spikings (CVPR 2024 · 6 citations) |
| Add MTDC module | S-CIF · accuracy | 55.1% -> 57.6% | Helped | Recognizing Ultra-High-Speed Moving Objects with Bio-Inspired Spike Camera (AAAI 2024 · 5 citations) |
| Add refinement network | Basketball · PSNR | 24.01 -> 27.23 | Helped | EVS-assisted Joint Deblurring Rolling-Shutter Correction and Video Frame Interpolation through Sensor Inverse Modeling (CVPR 2024 · 5 citations) |
| add the extractor | DAIR-V2X test, 0 ms delay · mAP@3D IoU0.3 | 31.72 -> 33.40 | Helped | BEVSync: Asynchronous Data Alignment for Camera-based Vehicle-Infrastructure Cooperative Perception Under Uncertain Delays (AAAI 2025 · 4 citations) |
What reviewers will expect
Datasets and baselines named in the 20 papers of this approach from 2024–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.
Datasets
- REDS · 2 of 20 papers
- Vimeo90K · 2 of 20 papers
Baselines
- REFID · 3 of 20 papers
- EDI · 2 of 20 papers
- TFP · 2 of 20 papers
- EvUnroll · 2 of 20 papers
- HINet · 2 of 20 papers
- NAFNet · 2 of 20 papers
- EFNet · 2 of 20 papers
- TFI · 2 of 20 papers
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 38 papers; from OpenAlex and the papers' affiliations).
- Peking University · 7 papers
- University of Science and Technology of China · 2 papers
- Northwestern Polytechnical University · 2 papers
Use it
Download BibTeX of 36 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
- Learned optical flow estimation (73 papers)
- Video frame interpolation (60 papers)
- Event-based video reconstruction (63 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).