Spiking sampling network for image sparse representation and dynamic vision sensor data compression

TL;DR

This paper introduces a spiking sampling network that dynamically selects pixels for sparse image representation, improving reconstruction and enabling efficient compression of dynamic vision sensor data.

Contribution

It proposes a novel spiking neuron-based sampling network that adaptively determines pixel retention, enhancing sparse representation and data compression for vision applications.

Findings

Better image reconstruction compared to random sampling

Effective compression of dynamic vision sensor data

Reduces storage requirements significantly

Abstract

Sparse representation has attracted great attention because it can greatly save storage resources and find representative features of data in a low-dimensional space. As a result, it may be widely applied in engineering domains including feature extraction, compressed sensing, signal denoising, picture clustering, and dictionary learning, just to name a few. In this paper, we propose a spiking sampling network. This network is composed of spiking neurons, and it can dynamically decide which pixel points should be retained and which ones need to be masked according to the input. Our experiments demonstrate that this approach enables better sparse representation of the original image and facilitates image reconstruction compared to random sampling. We thus use this approach for compressing massive data from the dynamic vision sensor, which greatly reduces the storage requirements for event data.