Fig. 3: Performance comparison between state-of-the-art architectures for optical flow estimation on the MVSEC80 dataset. | Communications Engineering

Fig. 3: Performance comparison between state-of-the-art architectures for optical flow estimation on the MVSEC80 dataset.

From: Neuromorphic computing for robotic vision: algorithms to hardware advances

Fig. 3

SOTA baselines (EvFlow-Net50, Spike-FlowNet19 and Fusion-FlowNet18 have their average endpoint error (AEE) depicted on the left. The right side compares the AEE between fully-ANN and fully-SNN architectures with decreasing model sizes. (Data taken with permission from Adaptive-SpikeNet64. Copyright 2023, IEEE).

Back to article page