MEEV: Body Mesh Estimation On Egocentric Video
This work solves the specific problem of body mesh estimation in egocentric video for applications in human-computer interaction, but it is incremental as it builds on existing datasets and methods.
The paper tackles the problem of estimating human body mesh from egocentric video, addressing challenges like occlusions and blurry images, and achieves 82.30 MPJPE and 92.93 MPVPE, winning the EgoBody Challenge at ECCV 2022.
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