Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Text-driven Human Motion Generation with Motion Masked Diffusion Model

Xingyu Chen

TL;DR

The proposed Motion Masked Diffusion Model (MMDM) is a novel human motion masked mechanism for diffusion model to explicitly enhance its ability to learn the spatio-temporal relationships from contextual joints among motion sequences.

Abstract

Text-driven human motion generation is a multimodal task that synthesizes human motion sequences conditioned on natural language. It requires the model to satisfy textual descriptions under varying conditional inputs, while generating plausible and realistic human actions with high diversity. Existing diffusion model-based approaches have outstanding performance in the diversity and multimodality of generation. However, compared to autoregressive methods that train motion encoders before inference, diffusion methods lack in fitting the distribution of human motion features which leads to an unsatisfactory FID score. One insight is that the diffusion model lack the ability to learn the motion relations among spatio-temporal semantics through contextual reasoning. To solve this issue, in this paper, we proposed Motion Masked Diffusion Model \textbf{(MMDM)}, a novel human motion masked mechanism for diffusion model to explicitly enhance its ability to learn the spatio-temporal relationships from contextual joints among motion sequences. Besides, considering the complexity of human motion data with dynamic temporal characteristics and spatial structure, we designed two mask modeling strategies: \textbf{time frames mask} and \textbf{body parts mask}. During training, MMDM masks certain tokens in the motion embedding space. Then, the diffusion decoder is designed to learn the whole motion sequence from masked embedding in each sampling step, this allows the model to recover a complete sequence from incomplete representations. Experiments on HumanML3D and KIT-ML dataset demonstrate that our mask strategy is effective by balancing motion quality and text-motion consistency.

Text-driven Human Motion Generation with Motion Masked Diffusion Model

TL;DR

The proposed Motion Masked Diffusion Model (MMDM) is a novel human motion masked mechanism for diffusion model to explicitly enhance its ability to learn the spatio-temporal relationships from contextual joints among motion sequences.

Abstract

Text-driven human motion generation is a multimodal task that synthesizes human motion sequences conditioned on natural language. It requires the model to satisfy textual descriptions under varying conditional inputs, while generating plausible and realistic human actions with high diversity. Existing diffusion model-based approaches have outstanding performance in the diversity and multimodality of generation. However, compared to autoregressive methods that train motion encoders before inference, diffusion methods lack in fitting the distribution of human motion features which leads to an unsatisfactory FID score. One insight is that the diffusion model lack the ability to learn the motion relations among spatio-temporal semantics through contextual reasoning. To solve this issue, in this paper, we proposed Motion Masked Diffusion Model \textbf{(MMDM)}, a novel human motion masked mechanism for diffusion model to explicitly enhance its ability to learn the spatio-temporal relationships from contextual joints among motion sequences. Besides, considering the complexity of human motion data with dynamic temporal characteristics and spatial structure, we designed two mask modeling strategies: \textbf{time frames mask} and \textbf{body parts mask}. During training, MMDM masks certain tokens in the motion embedding space. Then, the diffusion decoder is designed to learn the whole motion sequence from masked embedding in each sampling step, this allows the model to recover a complete sequence from incomplete representations. Experiments on HumanML3D and KIT-ML dataset demonstrate that our mask strategy is effective by balancing motion quality and text-motion consistency.
Paper Structure (13 sections, 9 equations, 2 figures, 4 tables)

This paper contains 13 sections, 9 equations, 2 figures, 4 tables.

Table of Contents

  1. Introduction
  2. RELATED WORKS
  3. METHODOLOGY
  4. human motion diffusion model
  5. Motion embedding Masked Diffusion
  6. Time frames mask
  7. Body parts mask
  8. EXPERIMENTS
  9. Set up
  10. Results and Analysis
  11. Ablation Study on Masking Mechanism
  12. Ablation Study on Model Architecture
  13. Conclusion

Figures (2)

  • Figure 1: (a) Visualization for text-driven human motion sequence. Our method balances the generation quality and diversity of the high-fidelity motion with the semantic consistency of the textual descriptions. (b) Performance in HumanML3D dataset.FID (lower is better) and Multimodality (higher is better) metrics the generation quality and average variance of motion sequences.
  • Figure 2: Overview and network. We propose motion mask diffusion model (Left), including time frames mask (Middle) and body parts mask (Right) for expressive spatio-temporal features in the motion embedding. Given a natural language condition, a CLIP radford2021learning transfer it into textual embedding and projected together with positional embedding of timestep $t$ for classifier-free learning ho2022classifier. In each sampling step, our model follow MDM tevet2023human directly predicts the final clean motion sequence ${x}^{1:N}$ instead of noise, then repeats from $x_t$ to $x_0$.