MEEV: Body Mesh Estimation On Egocentric Video

21 Oct 2022  ·  Nicolas Monet, Dongyoon Wee ·

This technical report introduces our solution, MEEV, proposed to the EgoBody Challenge at ECCV 2022. Captured from head-mounted devices, the dataset consists of human body shape and motion of interacting people. The EgoBody dataset has challenges such as occluded body or blurry image. In order to overcome the challenges, MEEV is designed to exploit multiscale features for rich spatial information. Besides, to overcome the limited size of dataset, the model is pre-trained with the dataset aggregated 2D and 3D pose estimation datasets. Achieving 82.30 for MPJPE and 92.93 for MPVPE, MEEV has won the EgoBody Challenge at ECCV 2022, which shows the effectiveness of the proposed method. The code is available at https://github.com/clovaai/meev

PDF Abstract

Results from the Paper


 Ranked #1 on 3D human pose and shape estimation on EgoBody (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
3D Human Pose Estimation 3DPW MEEV MPJPE 81.74 # 71
3D human pose and shape estimation EgoBody MEEV Average MPJPE (mm) 82.3032 # 1
PA-MPJPE 55.1292 # 1
MPVPE 92.9391 # 1
PA-MPVPE 62.9764 # 1

Methods


No methods listed for this paper. Add relevant methods here