Event-Enhanced Snapshot Compressive Videography at 10K FPS
Not on the map. Why?
Abstract (arXiv)
Video snapshot compressive imaging (SCI) encodes the target dynamic scene compactly into a snapshot and reconstructs its high-speed frame sequence afterward, greatly reducing the required data footprint and transmission bandwidth as well as enabling high-speed imaging with a low frame rate intensity camera. In implementation, high-speed dynamics are encoded via temporally varying patterns, and only frames at corresponding temporal intervals can be reconstructed, while the dynamics occurring between consecutive frames are lost. To unlock the potential of conventional snapshot compressive videography, we propose a novel hybrid "intensity+event" imaging scheme by incorporating an event camera into a video SCI setup. Our proposed system consists of a dual-path optical setup to record the coded intensity measurement and intermediate event signals simultaneously, which is compact and photon-efficient by collecting the half photons discarded in conventional video SCI. Correspondingly, we developed a dual-branch Transformer utilizing the reciprocal relationship between two data modes to decode dense video frames. Extensive experiments on both simulated and real-captured data demonstrate our superiority to state-of-the-art video SCI and video frame interpolation (VFI) methods. Benefiting from the new hybrid design leveraging both intrinsic redundancy in videos and the unique feature of event cameras, we achieve high-quality videography at 0.1ms time intervals with a low-cost CMOS image sensor working at 24 FPS.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 32 of its 58 references that are in the map. First posted on arXiv 11 Apr 2024.
Builds on
32 of 58 references.
References · 32
- 2017Attention Is All You Needcited by 59,932
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2017The 2017 DAVIS Challenge on Video Object Segmentationcited by 942
- 2015Empirical Evaluation of Rectified Activations in Convolutional Networkcited by 515
- 2018Unsupervised Event-based Learning of Optical Flow, Depth, and Egomotioncited by 304
- 2019Depth-Aware Video Frame Interpolationcited by 232
- 2019End-to-End Learning of Representations for Asynchronous Event-Based Datacited by 216
- 2018HATS: Histograms of Averaged Time Surfaces for Robust Event-based Object Classificationcited by 215
- 2017Video Frame Interpolation via Adaptive Separable Convolutioncited by 211
- 2020Real-Time Intermediate Flow Estimation for Video Frame Interpolationcited by 211
- 2019Video to Events: Recycling Video Datasets for Event Camerascited by 162
- 2017Video Frame Interpolation via Adaptive Convolutioncited by 158
20 more
- 2018Context-aware Synthesis for Video Frame Interpolationcited by 153
- 2021TimeLens: Event-based Video Frame Interpolationcited by 150
- 2019AdaCoF: Adaptive Collaboration of Flows for Video Frame Interpolationcited by 133
- 2021XVFI: eXtreme Video Frame Interpolationcited by 123
- 2021Video Frame Interpolation Transformercited by 122
- 2022Time Lens++: Event-based Frame Interpolation with Parametric Non-linear Flow and Multi-scale Fusioncited by 110
- 2018Rank Minimization for Snapshot Compressive Imagingcited by 99
- 2020FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolationcited by 97
- 2020Plug-and-Play Algorithms for Large-scale Snapshot Compressive Imagingcited by 78
- 2018PhaseNet for Video Frame Interpolationcited by 61
- 2013Coded aperture compressive temporal imagingcited by 57
- 2020GAP-net for Snapshot Compressive Imagingcited by 54
- 2015HFirst: A Temporal Approach to Object Recognitioncited by 50
- 2020EventSR: From Asynchronous Events to Image Reconstruction, Restoration, and Super-Resolution via End-to-End Adversarial Learningcited by 40
- 2021Memory-Efficient Network for Large-scale Video Compressive Sensingcited by 30
- 2021MetaSCI: Scalable and Adaptive Reconstruction for Video Compressive Sensingcited by 29
- 2019Learning to Super Resolve Intensity Images from Eventscited by 26
- 2022Spatial-Temporal Transformer for Video Snapshot Compressive Imagingcited by 21
- 2022Adaptive Deep PnP Algorithm for Video Snapshot Compressive Imagingcited by 10
- 2021Dual-view Snapshot Compressive Imaging via Optical Flow Aided Recurrent Neural Networkcited by 1
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.