Aquatic Neuromorphic Optical Flow
It addresses the bottleneck of data scarcity and resource constraints in underwater perception, enabling lightweight, real-time motion estimation for agile underwater robots.
This work pioneers the use of event cameras and spiking neural networks for self-supervised optical flow estimation in underwater environments, achieving competitive accuracy with superior computational efficiency and bypassing the need for labeled data.
Underwater environments impose severe constraints on conventional imaging systems and demand solutions that balance high-quality sensing with strict resource efficiency. While emerging event cameras offer a promising alternative, their potential in aquatic scenarios remains largely unexplored. Through the lens of neuromorphic vision, this work pioneers the investigation of motion fields that serve as key media for agile underwater perception. Built upon spiking neural networks, we introduce a self-supervised framework to estimate per-pixel optical flow from asynchronous event streams, elegantly bypassing the long-standing bottleneck of underwater data scarcity. Extensive evaluations demonstrate that our method achieves competitive visual and quantitative results against leading techniques while operating with superior computational efficiency. By bridging neuromorphic sensing and aquatic intelligence, this work opens new frontiers for lightweight, real-time, and low-cost perception on resource-constrained underwater edge platforms.