SpikeCodec: An End-to-end Learned Compression Framework for Spiking Camera

TL;DR

This paper introduces SpikeCodec, a novel end-to-end learned compression framework specifically designed for spike camera data, leveraging scene recovery and variational auto-encoders to efficiently reduce data size while maintaining fidelity.

Contribution

It presents the first data-trained model tailored for spike stream compression, addressing unique challenges of spike camera data with a robust, scene-aware approach.

Findings

Outperforms conventional codecs in compression efficiency

Maintains high fidelity of reconstructed spike streams

Provides a strong baseline for future learned spike data compression

Abstract

Recently, the bio-inspired spike camera with continuous motion recording capability has attracted tremendous attention due to its ultra high temporal resolution imaging characteristic. Such imaging feature results in huge data storage and transmission burden compared to that of traditional camera, raising severe challenge and imminent necessity in compression for spike camera captured content. Existing lossy data compression methods could not be applied for compressing spike streams efficiently due to integrate-and-fire characteristic and binarized data structure. Considering the imaging principle and information fidelity of spike cameras, we introduce an effective and robust representation of spike streams. Based on this representation, we propose a novel learned spike compression framework using scene recovery, variational auto-encoder plus spike simulator. To our knowledge, it is the first data-trained model for efficient and robust spike stream compression. Extensive experimental results show that our method outperforms the conventional and learning-based codecs, contributing a strong baseline for learned spike data compression.