Gesture2Text: A Generalizable Decoder for Word-Gesture Keyboards in XR Through Trajectory Coarse Discretization and Pre-training

TL;DR

This paper introduces a pre-trained neural decoder for word-gesture keyboards in XR that achieves high accuracy, generalizes across different systems, and operates efficiently in real-time, outperforming existing methods.

Contribution

It presents a novel pre-training approach on coarse gesture data, enabling a generalizable, accurate, and lightweight neural decoder for XR word-gesture keyboards.

Findings

Achieves 90.4% Top-4 accuracy across four datasets.

Outperforms SHARK^2 by 37.2% in accuracy.

Operates in 97 ms on Quest 3 with only 4 MB size.

Abstract

Text entry with word-gesture keyboards (WGK) is emerging as a popular method and becoming a key interaction for Extended Reality (XR). However, the diversity of interaction modes, keyboard sizes, and visual feedback in these environments introduces divergent word-gesture trajectory data patterns, thus leading to complexity in decoding trajectories into text. Template-matching decoding methods, such as SHARK^2, are commonly used for these WGK systems because they are easy to implement and configure. However, these methods are susceptible to decoding inaccuracies for noisy trajectories. While conventional neural-network-based decoders (neural decoders) trained on word-gesture trajectory data have been proposed to improve accuracy, they have their own limitations: they require extensive data for training and deep-learning expertise for implementation. To address these challenges, we propose a novel solution that combines ease of implementation with high decoding accuracy: a generalizable neural decoder enabled by pre-training on large-scale coarsely discretized word-gesture trajectories. This approach produces a ready-to-use WGK decoder that is generalizable across mid-air and on-surface WGK systems in augmented reality (AR) and virtual reality (VR), which is evident by a robust average Top-4 accuracy of 90.4% on four diverse datasets. It significantly outperforms SHARK^2 with a 37.2% enhancement and surpasses the conventional neural decoder by 7.4%. Moreover, the Pre-trained Neural Decoder's size is only 4 MB after quantization, without sacrificing accuracy, and it can operate in real-time, executing in just 97 milliseconds on Quest 3.