StereoSpike: Depth Learning with a Spiking Neural Network

TL;DR

StereoSpike introduces a neuromorphic deep learning approach using spiking neural networks and event-based cameras for accurate, low-power depth estimation, demonstrating state-of-the-art results and efficient implementation potential.

Contribution

It presents the first large-scale regression solution with a fully spiking neural network for depth estimation, combining a novel readout and regularization for low firing rates.

Findings

Achieves state-of-the-art depth estimation accuracy.

Operates with low firing rates (<10%) via regularization.

Demonstrates potential for efficient neuromorphic hardware deployment.

Abstract

Depth estimation is an important computer vision task, useful in particular for navigation in autonomous vehicles, or for object manipulation in robotics. Here we solved it using an end-to-end neuromorphic approach, combining two event-based cameras and a Spiking Neural Network (SNN) with a slightly modified U-Net-like encoder-decoder architecture, that we named StereoSpike. More specifically, we used the Multi Vehicle Stereo Event Camera Dataset (MVSEC). It provides a depth ground-truth, which was used to train StereoSpike in a supervised manner, using surrogate gradient descent. We propose a novel readout paradigm to obtain a dense analog prediction -- the depth of each pixel -- from the spikes of the decoder. We demonstrate that this architecture generalizes very well, even better than its non-spiking counterparts, leading to state-of-the-art test accuracy. To the best of our knowledge, it is the first time that such a large-scale regression problem is solved by a fully spiking network. Finally, we show that low firing rates (<10%) can be obtained via regularization, with a minimal cost in accuracy. This means that StereoSpike could be efficiently implemented on neuromorphic chips, opening the door for low power and real time embedded systems.