AdvMT: Adversarial Motion Transformer for Long-term Human Motion Prediction

TL;DR

AdvMT introduces an adversarial transformer model that improves long-term human motion prediction accuracy by capturing spatial-temporal dependencies and reducing artifacts through adversarial training.

Contribution

The paper presents a novel Adversarial Motion Transformer that combines transformer encoding with adversarial training for more realistic long-term human motion prediction.

Findings

Significantly improves long-term prediction accuracy.

Reduces artifacts in predicted human motions.

Enhances robustness of short-term predictions.

Abstract

To achieve seamless collaboration between robots and humans in a shared environment, accurately predicting future human movements is essential. Human motion prediction has traditionally been approached as a sequence prediction problem, leveraging historical human motion data to estimate future poses. Beginning with vanilla recurrent networks, the research community has investigated a variety of methods for learning human motion dynamics, encompassing graph-based and generative approaches. Despite these efforts, achieving accurate long-term predictions continues to be a significant challenge. In this regard, we present the Adversarial Motion Transformer (AdvMT), a novel model that integrates a transformer-based motion encoder and a temporal continuity discriminator. This combination effectively captures spatial and temporal dependencies simultaneously within frames. With adversarial training, our method effectively reduces the unwanted artifacts in predictions, thereby ensuring the learning of more realistic and fluid human motions. The evaluation results indicate that AdvMT greatly enhances the accuracy of long-term predictions while also delivering robust short-term predictions