UniHPE: Towards Unified Human Pose Estimation via Contrastive Learning

24 Nov 2023  ·  Zhongyu Jiang, Wenhao Chai, Lei LI, Zhuoran Zhou, Cheng-Yen Yang, Jenq-Neng Hwang ·

In recent times, there has been a growing interest in developing effective perception techniques for combining information from multiple modalities. This involves aligning features obtained from diverse sources to enable more efficient training with larger datasets and constraints, as well as leveraging the wealth of information contained in each modality. 2D and 3D Human Pose Estimation (HPE) are two critical perceptual tasks in computer vision, which have numerous downstream applications, such as Action Recognition, Human-Computer Interaction, Object tracking, etc. Yet, there are limited instances where the correlation between Image and 2D/3D human pose has been clearly researched using a contrastive paradigm. In this paper, we propose UniHPE, a unified Human Pose Estimation pipeline, which aligns features from all three modalities, i.e., 2D human pose estimation, lifting-based and image-based 3D human pose estimation, in the same pipeline. To align more than two modalities at the same time, we propose a novel singular value based contrastive learning loss, which better aligns different modalities and further boosts the performance. In our evaluation, UniHPE achieves remarkable performance metrics: MPJPE $50.5$mm on the Human3.6M dataset and PAMPJPE $51.6$mm on the 3DPW dataset. Our proposed method holds immense potential to advance the field of computer vision and contribute to various applications.

PDF Abstract

Results from the Paper


Ranked #68 on 3D Human Pose Estimation on 3DPW (PA-MPJPE metric)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Human Pose Estimation 3DPW UniHPE-w48 PA-MPJPE 65.7 # 115
3D Human Pose Estimation 3DPW UniHPE (GT) PA-MPJPE 51.6 # 68
3D Human Pose Estimation Human3.6M UniHPE-w48 Average MPJPE (mm) 50.5 # 180
PA-MPJPE 36.2 # 39
3D Human Pose Estimation Human3.6M UniHPE (GT) Average MPJPE (mm) 53.6 # 219
PA-MPJPE 40.9 # 70

Methods