Referring Human Pose and Mask Estimation in the Wild

TL;DR

This paper introduces R-HPM, a new task for identifying and estimating human pose and masks based on text or positional prompts, supported by a large annotated dataset and a novel promptable model, UniPHD.

Contribution

The paper presents the first end-to-end promptable approach for R-HPM and introduces the RefHuman dataset with extensive annotations for this task.

Findings

UniPHD achieves high-quality, prompt-conditioned human pose and mask estimation.

RefHuman dataset contains over 50,000 annotated instances with prompts, keypoints, and masks.

The approach outperforms existing methods on benchmark datasets.

Abstract

We introduce Referring Human Pose and Mask Estimation (R-HPM) in the wild, where either a text or positional prompt specifies the person of interest in an image. This new task holds significant potential for human-centric applications such as assistive robotics and sports analysis. In contrast to previous works, R-HPM (i) ensures high-quality, identity-aware results corresponding to the referred person, and (ii) simultaneously predicts human pose and mask for a comprehensive representation. To achieve this, we introduce a large-scale dataset named RefHuman, which substantially extends the MS COCO dataset with additional text and positional prompt annotations. RefHuman includes over 50,000 annotated instances in the wild, each equipped with keypoint, mask, and prompt annotations. To enable prompt-conditioned estimation, we propose the first end-to-end promptable approach named UniPHD for R-HPM. UniPHD extracts multimodal representations and employs a proposed pose-centric hierarchical decoder to process (text or positional) instance queries and keypoint queries, producing results specific to the referred person. Extensive experiments demonstrate that UniPHD produces quality results based on user-friendly prompts and achieves top-tier performance on RefHuman val and MS COCO val2017. Data and Code: https://github.com/bo-miao/RefHuman