SpikeVPR combines event cameras with spiking neural networks and EventDilation augmentation to achieve visual place recognition performance comparable to deep networks but with 50x fewer parameters and 30-250x lower energy use.
On the Integration of Space, Time, and Memory
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
-
Event-Driven Neuromorphic Vision Enables Energy-Efficient Visual Place Recognition
SpikeVPR combines event cameras with spiking neural networks and EventDilation augmentation to achieve visual place recognition performance comparable to deep networks but with 50x fewer parameters and 30-250x lower energy use.