SaccadeNet: Towards Real-time Saccade Prediction for Virtual Reality Infinite Walking
The preprint of our paper SaccadeNet: Towards Real-time Saccade Prediction for Virtual Reality Infinite Walking is available on arxiv.org. The work is co-authored by Yashas Joshi and Charalambos Poullis.
TL;DR: We propose a deep neural network for predicting saccades in VR applications of moderate cognitive workload. During saccades, users exhibit temporary blindness which we exploit for redirection. This work extends our previous paper and patent by eliminating the need for a high-end eye-tracker. US & Canada patents are pending.
0:00
/