English

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

Computer Vision and Pattern Recognition 2025-11-12 v1

Abstract

Spiking neural networks (SNNs) promise highly energy-efficient computing, but their adoption is hindered by a critical scarcity of event-stream data. This work introduces I2E, an algorithmic framework that resolves this bottleneck by converting static images into high-fidelity event streams. By simulating microsaccadic eye movements with a highly parallelized convolution, I2E achieves a conversion speed over 300x faster than prior methods, uniquely enabling on-the-fly data augmentation for SNN training. The framework's effectiveness is demonstrated on large-scale benchmarks. An SNN trained on the generated I2E-ImageNet dataset achieves a state-of-the-art accuracy of 60.50%. Critically, this work establishes a powerful sim-to-real paradigm where pre-training on synthetic I2E data and fine-tuning on the real-world CIFAR10-DVS dataset yields an unprecedented accuracy of 92.5%. This result validates that synthetic event data can serve as a high-fidelity proxy for real sensor data, bridging a long-standing gap in neuromorphic engineering. By providing a scalable solution to the data problem, I2E offers a foundational toolkit for developing high-performance neuromorphic systems. The open-source algorithm and all generated datasets are provided to accelerate research in the field.

Keywords

Cite

@article{arxiv.2511.08065,
  title  = {I2E: Real-Time Image-to-Event Conversion for High-Performance Spiking Neural Networks},
  author = {Ruichen Ma and Liwei Meng and Guanchao Qiao and Ning Ning and Yang Liu and Shaogang Hu},
  journal= {arXiv preprint arXiv:2511.08065},
  year   = {2025}
}

Comments

AAAI-26 Oral

R2 v1 2026-07-01T07:31:43.851Z