Generative Model-Enhanced Human Motion Prediction

TL;DR

This paper introduces a new out-of-distribution benchmark for human motion prediction and proposes a hybrid generative-discriminative framework that enhances robustness to distributional shifts without losing in-distribution accuracy.

Contribution

The paper presents a novel OoD benchmark for human motion prediction and a hybrid framework that improves model robustness to distributional shifts by augmenting discriminative models with generative components.

Findings

Improved OoD robustness in discriminative models

Maintained in-distribution performance

Theoretical benefits for model interpretability

Abstract

The task of predicting human motion is complicated by the natural heterogeneity and compositionality of actions, necessitating robustness to distributional shifts as far as out-of-distribution (OoD). Here we formulate a new OoD benchmark based on the Human3.6M and CMU motion capture datasets, and introduce a hybrid framework for hardening discriminative architectures to OoD failure by augmenting them with a generative model. When applied to current state-of-the-art discriminative models, we show that the proposed approach improves OoD robustness without sacrificing in-distribution performance, and can theoretically facilitate model interpretability. We suggest human motion predictors ought to be constructed with OoD challenges in mind, and provide an extensible general framework for hardening diverse discriminative architectures to extreme distributional shift. The code is available at https://github.com/bouracha/OoDMotion.