A Robust Visual Sampling Model Inspired by Receptive Field

TL;DR

This paper introduces a robust visual sampling model inspired by receptive fields that enhances spike camera image reconstruction and noise filtering, demonstrating improved performance on a new high-speed motion dataset.

Contribution

The proposed RVSM model uses wavelet-based receptive fields to improve spike camera sampling robustness and generalizes well to other neuromorphic sensors.

Findings

Improved image reconstruction quality from spike data.

Enhanced noise filtering capabilities.

Effective in various motion scenes.

Abstract

Spike camera mimicking the retina fovea can report per-pixel luminance intensity accumulation by firing spikes. As a bio-inspired vision sensor with high temporal resolution, it has a huge potential for computer vision. However, the sampling model in current Spike camera is so susceptible to quantization and noise that it cannot capture the texture details of objects effectively. In this work, a robust visual sampling model inspired by receptive field (RVSM) is proposed where wavelet filter generated by difference of Gaussian (DoG) and Gaussian filter are used to simulate receptive field. Using corresponding method similar to inverse wavelet transform, spike data from RVSM can be converted into images. To test the performance, we also propose a high-speed motion spike dataset (HMD) including a variety of motion scenes. By comparing reconstructed images in HMD, we find RVSM can improve the ability of capturing information of Spike camera greatly. More importantly, due to mimicking receptive field mechanism to collect regional information, RVSM can filter high intensity noise effectively and improves the problem that Spike camera is sensitive to noise largely. Besides, due to the strong generalization of sampling structure, RVSM is also suitable for other neuromorphic vision sensor. Above experiments are finished in a Spike camera simulator.