FreeMan: Towards Benchmarking 3D Human Pose Estimation under Real-World Conditions

TL;DR

FreeMan introduces a large-scale, real-world multi-view dataset for 3D human pose estimation, addressing the limitations of existing datasets and facilitating progress in real-world applications.

Contribution

The paper presents FreeMan, the first extensive multi-view dataset captured in diverse real-world scenarios for 3D human pose estimation.

Findings

FreeMan contains 11 million frames from 8,000 sequences across various scenarios.

Baseline evaluations highlight the dataset's complexity and challenges.

FreeMan demonstrates robust transferability to real-world conditions.

Abstract

Estimating the 3D structure of the human body from natural scenes is a fundamental aspect of visual perception. 3D human pose estimation is a vital step in advancing fields like AIGC and human-robot interaction, serving as a crucial technique for understanding and interacting with human actions in real-world settings. However, the current datasets, often collected under single laboratory conditions using complex motion capture equipment and unvarying backgrounds, are insufficient. The absence of datasets on variable conditions is stalling the progress of this crucial task. To facilitate the development of 3D pose estimation, we present FreeMan, the first large-scale, multi-view dataset collected under the real-world conditions. FreeMan was captured by synchronizing 8 smartphones across diverse scenarios. It comprises 11M frames from 8000 sequences, viewed from different perspectives. These sequences cover 40 subjects across 10 different scenarios, each with varying lighting conditions. We have also established an semi-automated pipeline containing error detection to reduce the workload of manual check and ensure precise annotation. We provide comprehensive evaluation baselines for a range of tasks, underlining the significant challenges posed by FreeMan. Further evaluations of standard indoor/outdoor human sensing datasets reveal that FreeMan offers robust representation transferability in real and complex scenes. Code and data are available at https://wangjiongw.github.io/freeman.