Neuromorphic Optical Flow and Real-time Implementation with Event Cameras. (arXiv:2304.07139v1 [cs.CV])

Optical flow provides information on relative motion that is an important
component in many computer vision pipelines. Neural networks provide high
accuracy optical flow, yet their complexity is often prohibitive for
application at the edge or in robots, where efficiency and latency play crucial
role. To address this challenge, we build on the latest developments in
event-based vision and spiking neural networks. We propose a new network
architecture, inspired by Timelens, that improves the state-of-the-art
self-supervised optical flow accuracy when …

accuracy application architecture art arxiv cameras challenge complexity computer computer vision edge efficiency event flow implementation information latency network network architecture networks neural networks neuromorphic optical flow pipelines real-time robots role spiking neural networks state the edge vision