ML Anthology

Image Reconstruction from Neuromorphic Event Cameras Using Laplacian-Prediction and Poisson Integration with Spiking and Artificial Neural Networks

Hadar Cohen Duwek, Albert Shalumov, Elishai Ezra Tsur
CVPRW 2021 pp. 1333-1341
doi:10.1109/CVPRW53098.2021.00147 /cvprw/2021/duwek2021cvprw-image/

Abstract

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.

PDF CVPRW Semantic Scholar

Cite

Text

Duwek et al. "Image Reconstruction from Neuromorphic Event Cameras Using Laplacian-Prediction and Poisson Integration with Spiking and Artificial Neural Networks." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021. doi:10.1109/CVPRW53098.2021.00147

Markdown

[Duwek et al. "Image Reconstruction from Neuromorphic Event Cameras Using Laplacian-Prediction and Poisson Integration with Spiking and Artificial Neural Networks." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021.](https://mlanthology.org/cvprw/2021/duwek2021cvprw-image/) doi:10.1109/CVPRW53098.2021.00147

BibTeX

@inproceedings{duwek2021cvprw-image,
  title     = {{Image Reconstruction from Neuromorphic Event Cameras Using Laplacian-Prediction and Poisson Integration with Spiking and Artificial Neural Networks}},
  author    = {Duwek, Hadar Cohen and Shalumov, Albert and Tsur, Elishai Ezra},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2021},
  pages     = {1333-1341},
  doi       = {10.1109/CVPRW53098.2021.00147},
  url       = {https://mlanthology.org/cvprw/2021/duwek2021cvprw-image/}
}