CigTime: Corrective Instruction Generation Through Inverse Motion Editing

TL;DR

This paper introduces CigTime, a novel method for generating corrective instructional text from motion data, improving motion editing and guidance in sports and motor skill learning.

Contribution

It presents a new inverse motion editing approach that leverages large language models and motion frameworks to generate corrective instructions from source and target motions.

Findings

Significant improvement over baseline methods in qualitative assessments.

Effective generation of corrective instructions across diverse applications.

Demonstrated applicability in sports coaching and motor skill learning.

Abstract

Recent advancements in models linking natural language with human motions have shown significant promise in motion generation and editing based on instructional text. Motivated by applications in sports coaching and motor skill learning, we investigate the inverse problem: generating corrective instructional text, leveraging motion editing and generation models. We introduce a novel approach that, given a user's current motion (source) and the desired motion (target), generates text instructions to guide the user towards achieving the target motion. We leverage large language models to generate corrective texts and utilize existing motion generation and editing frameworks to compile datasets of triplets (source motion, target motion, and corrective text). Using this data, we propose a new motion-language model for generating corrective instructions. We present both qualitative and quantitative results across a diverse range of applications that largely improve upon baselines. Our approach demonstrates its effectiveness in instructional scenarios, offering text-based guidance to correct and enhance user performance.