SpikeCV is a new open-source computer vision platform for the spike camera. You can Learn more about SpikeCV here.
🔝📌 Hiring! We have multiple openings for interns! [Details]
The Award Ceremony of the SpikeCV Ultra-High-Speed Vision Challenge was successfully held at PRCV 2025 in Shanghai! 🎉
Our paper “SpikeCV: Open a Continuous Computer Vision Era” has been accepted by SCIENCE CHINA Information Sciences and is now available online. 🎉
The Award Ceremony of the 1st SpikeCV International Challenge was successfully held at IJCAI 2025 in Guangzhou! 🎉
The first spike‑codec paper, “A Joint Visual Compression and Perception Framework for Neuromorphic Spiking Camera,” was published in IEEE TIP! Congratulations to Kexiang Feng, Chuanmin Jia, Siwei Ma, and Wen Gao!
We held the SpikeCV Challenge at PRCV 2025: Ultra-high-speed Spike Vision Dataset and Open Task Challenge. 🚀
Providing dataset for color spike camera reconstruction, which consists of 28 Bayer-pattern spike stream (BSS) clips."
Adding algorithm in "Learning a Deep Demosaicing Network for Spike Camera with Color Filter Array (TIP 24, Dong, et al.)". It includes train/evaluate codes for CSpkNet.
Adding algorithm in "Recognizing High-Speed Moving Objects with Spike Camera (ACM MM 23, Zhao, et al.)". It includes train/evaluate codes for HSSR.
Adding algorithm in "SpiReco: Fast and Efficient Recognition of High-Speed Moving Objects with Spike Cameras (TCSVT 23, Zhao, et al.)". It includes train/evaluate codes for SpiReco.
Adding algorithm in "Learning Super-Resolution Reconstruction for High Temporal Resolution Spike Stream (TCSVT 21, Xiang, et al.)". It includes test codes for SRR.
The form of formlessness · Spiking Continuous Photographing (ICHSIP-33)
We are the research team from Peking University. To build up a community ecology for the spike vision to facilitate more users to take advantage of the spike camera, our built SpikeCV provides a variety of ultra-high-speed scene datasets, hardware interfaces, and an easy-to-use modules library. SpikeCV focuses on encapsulation for spike data, standardization for dataset interfaces, modularization for vision tasks, and real-time applications for challenging scenes, which can be used as a Python library to fulfilled most of the numerical analysis needs of researchers
“工欲善其事，必先利其器。”
《论语》
We are committed to integrating algorithms, hardware and data into a unified interface for user utilization.
We offer open-source platform to the community for development.
We offer examples for using spike cameras to solve real visual tasks.