IP-STDP-FlowNet represents a spiking neural network (SNN) for optic flow estimation. It builds on top of the SNN presented in [1], but also utilizes adaptive neuron parameters. This increases its robustness to changes in the spatiotemporal properties of the input data.
Installation instructions will follow shortly
[1] Paredes-Vallés, K. Y. W. Scheper, and G. C. H. E. de Croon, “Unsupervised learning of a hierarchical spiking neural network for optical flow estimation: From events to global motion perception,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 42, no. 8, pp. 2051–2064, Mar. 2020