A self-supervised spiking neural network framework estimates optical flow from asynchronous underwater event streams without labeled data, achieving competitive accuracy with high computational efficiency.
Millisecond-scale behaviours of plankton quantified in vitro and in situ using the event-based vision sensor
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Aquatic Neuromorphic Optical Flow
A self-supervised spiking neural network framework estimates optical flow from asynchronous underwater event streams without labeled data, achieving competitive accuracy with high computational efficiency.