I2E: Real-Time Image-to-Event Conversion for High-Performance Spiking Neural Networks

The I2E algorithmic framework, introduced on November 12, 2025, addresses a critical challenge in the adoption of spiking neural networks (SNNs) by converting static images into event streams at speeds over 300 times faster than prior methods. This breakthrough allows for real-time data augmentation, significantly enhancing SNN training. The framework's effectiveness is validated through impressive performance metrics, achieving 60.50% accuracy on the I2E-ImageNet dataset and an unprecedented 92.5% accuracy on the CIFAR10-DVS dataset. These results underscore the capability of synthetic event data to serve as a high-fidelity proxy for real sensor data, bridging a longstanding gap in neuromorphic engineering. By providing a scalable solution to the data scarcity problem, I2E establishes a foundational toolkit for future developments in the field, potentially transforming the landscape of energy-efficient computing.