Human-M3: A Multi-view Multi-modal Dataset for 3D Human Pose Estimation in Outdoor Scenes

TL;DR

Human-M3 is a comprehensive outdoor multi-view, multi-modal dataset for 3D human pose estimation, featuring RGB videos and pointclouds, along with a novel annotation algorithm, advancing research in outdoor multi-person pose estimation.

Contribution

The paper introduces Human-M3, a new multi-modal, multi-view dataset with an annotation method, and demonstrates the benefits of multi-modal data for 3D human pose estimation.

Findings

The dataset is challenging and suitable for future research.

Multi-modal data improves 3D pose estimation accuracy.

The proposed annotation algorithm enhances ground truth reliability.

Abstract

3D human pose estimation in outdoor environments has garnered increasing attention recently. However, prevalent 3D human pose datasets pertaining to outdoor scenes lack diversity, as they predominantly utilize only one type of modality (RGB image or pointcloud), and often feature only one individual within each scene. This limited scope of dataset infrastructure considerably hinders the variability of available data. In this article, we propose Human-M3, an outdoor multi-modal multi-view multi-person human pose database which includes not only multi-view RGB videos of outdoor scenes but also corresponding pointclouds. In order to obtain accurate human poses, we propose an algorithm based on multi-modal data input to generate ground truth annotation. This benefits from robust pointcloud detection and tracking, which solves the problem of inaccurate human localization and matching ambiguity that may exist in previous multi-view RGB videos in outdoor multi-person scenes, and generates reliable ground truth annotations. Evaluation of multiple different modalities algorithms has shown that this database is challenging and suitable for future research. Furthermore, we propose a 3D human pose estimation algorithm based on multi-modal data input, which demonstrates the advantages of multi-modal data input for 3D human pose estimation. Code and data will be released on https://github.com/soullessrobot/Human-M3-Dataset.