DivDiff: A Conditional Diffusion Model for Diverse Human Motion Prediction

TL;DR

DivDiff is a novel conditional diffusion model that improves the diversity and realism of human motion prediction by integrating DCT, transformers, and a reinforcement sampling function to better control and generate plausible future motions.

Contribution

The paper introduces DivDiff, a diffusion-based model with DCT, transformers, and a reinforcement sampling function to enhance diversity and plausibility in human motion prediction.

Findings

Achieves high diversity and accuracy on Human3.6M and HumanEva-I datasets.

Effectively reduces noise disturbances during the diffusion process.

Outperforms existing methods in generating realistic human motions.

Abstract

Diverse human motion prediction (HMP) aims to predict multiple plausible future motions given an observed human motion sequence. It is a challenging task due to the diversity of potential human motions while ensuring an accurate description of future human motions. Current solutions are either low-diversity or limited in expressiveness. Recent denoising diffusion models (DDPM) hold potential generative capabilities in generative tasks. However, introducing DDPM directly into diverse HMP incurs some issues. Although DDPM can increase the diversity of the potential patterns of human motions, the predicted human motions become implausible over time because of the significant noise disturbances in the forward process of DDPM. This phenomenon leads to the predicted human motions being hard to control, seriously impacting the quality of predicted motions and restricting their practical applicability in real-world scenarios. To alleviate this, we propose a novel conditional diffusion-based generative model, called DivDiff, to predict more diverse and realistic human motions. Specifically, the DivDiff employs DDPM as our backbone and incorporates Discrete Cosine Transform (DCT) and transformer mechanisms to encode the observed human motion sequence as a condition to instruct the reverse process of DDPM. More importantly, we design a diversified reinforcement sampling function (DRSF) to enforce human skeletal constraints on the predicted human motions. DRSF utilizes the acquired information from human skeletal as prior knowledge, thereby reducing significant disturbances introduced during the forward process. Extensive results received in the experiments on two widely-used datasets (Human3.6M and HumanEva-I) demonstrate that our model obtains competitive performance on both diversity and accuracy.