MEEV: Body Mesh Estimation On Egocentric Video

October 21, 2022 · Entered Twilight · 🏛 arXiv.org

Repo contents: LICENSE, NOTICE, README.md, assets, common, data, environment.yml, experiments, main, tool

Authors Nicolas Monet, Dongyoon Wee arXiv ID 2210.14165 Category cs.CV: Computer Vision Citations 2 Venue arXiv.org Repository https://github.com/clovaai/meev ⭐ 13 Last Checked 3 months ago

Abstract

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