PackDiT: Joint Human Motion and Text Generation via Mutual Prompting
Preprint
Abstract
Human motion generation has advanced markedly with the advent of diffusion models. Most recent studies have concentrated on generating motion sequences based on text prompts, commonly referred to as text-to-motion generation. However, the bidirectional generation of motion and text, enabling tasks such as motion-to-text alongside text-to-motion, has been largely unexplored. This capability is essential for aligning diverse modalities and supports unconditional generation. In this paper, we introduce PackDiT, the first diffusion-based generative model capable of performing various tasks simultaneously, including motion generation, motion prediction, text generation, text-to-motion, motion-to-text, and joint motion-text generation. Our core innovation leverages mutual blocks to integrate multiple diffusion transformers (DiTs) across different modalities seamlessly. We train PackDiT on the HumanML3D dataset, achieving state-of-the-art text-to-motion performance with an FID score of 0.106, along with superior results in motion prediction and in-between tasks. Our experiments further demonstrate that diffusion models are effective for motion-to-text generation, achieving performance comparable to that of autoregressive models.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- Large Motion Model for Unified Multi-modal Motion Generation2024
- MotionDiffuse: Text-Driven Human Motion Generation With Diffusion ModelIEEE Transactions on Pattern Analysis and Machine Intelligence, 2024
- Human Motion Generation: A SurveyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
- DiffFashion: Reference-Based Fashion Design With Structure-Aware Transfer by Diffusion ModelsIEEE Transactions on Multimedia, 2023
- SMPL: A Skinned Multi-Person Linear Model2023
- Generating Human Motion from Textual Descriptions with Discrete Representations2023
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding2019