Event cameras are robust neuromorphic visual sensors, which communicate transients in luminance as events. Current paradigm for image reconstruction from event data relies on direct optimization of artificial Convolutional Neural Networks (CNNs). Here we proposed a two-phase neural network, which comprises a CNN, optimized for Laplacian prediction followed by a Spiking Neural Network (SNN) optimized for Poisson integration. By introducing Laplacian prediction into the pipeline, we provide image reconstruction with a network comprising only 200 parameters. We converted the CNN to SNN, providing a full neuromorphic implementation. We further optimized the network with Mish activation and a novel convoluted CNN design, proposing a hybrid of spiking and artificial neural network with < 100 parameters. Models were evaluated on both N-MNIST and N-Caltech101 datasets.
|Title of host publication||Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021|
|Publisher||IEEE Computer Society|
|Number of pages||9|
|State||Published - Jun 2021|
|Event||2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021 - Virtual, Online, United States|
Duration: 19 Jun 2021 → 25 Jun 2021
|Name||IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops|
|Conference||2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021|
|Period||19/06/21 → 25/06/21|
Bibliographical noteFunding Information:
This work was supported by the Israel Innovation Authority (EzerTech) and the Open University of Israel research grant.
© 2021 IEEE.