Multi-modal Pose Diffuser: A Multimodal Generative Conditional Pose Prior

TL;DR

MOPED introduces a multi-modal diffusion model as a human pose prior, enabling realistic pose generation conditioned on images and text, significantly improving pose estimation, denoising, and completion tasks.

Contribution

It is the first to utilize a multi-modal conditional diffusion model as a prior for SMPL pose parameters, enhancing pose realism and versatility.

Findings

Outperforms existing pose priors in multiple tasks

Captures a broader spectrum of plausible human poses

Effective in pose estimation, denoising, and completion

Abstract

The Skinned Multi-Person Linear (SMPL) model plays a crucial role in 3D human pose estimation, providing a streamlined yet effective representation of the human body. However, ensuring the validity of SMPL configurations during tasks such as human mesh regression remains a significant challenge , highlighting the necessity for a robust human pose prior capable of discerning realistic human poses. To address this, we introduce MOPED: \underline{M}ulti-m\underline{O}dal \underline{P}os\underline{E} \underline{D}iffuser. MOPED is the first method to leverage a novel multi-modal conditional diffusion model as a prior for SMPL pose parameters. Our method offers powerful unconditional pose generation with the ability to condition on multi-modal inputs such as images and text. This capability enhances the applicability of our approach by incorporating additional context often overlooked in traditional pose priors. Extensive experiments across three distinct tasks-pose estimation, pose denoising, and pose completion-demonstrate that our multi-modal diffusion model-based prior significantly outperforms existing methods. These results indicate that our model captures a broader spectrum of plausible human poses.