mlsanityData to 14 Oct 2026

MEEV: Body Mesh Estimation On Egocentric Video

arXiv 2210.14165 ↗First posted 21 Oct 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 8 of its 12 references that are in the map. First posted on arXiv 21 Oct 2022.

Builds on

8 of 12 references.

References · 8

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2022A ConvNet for the 2020scited by 3,579
  4. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  5. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 494
  6. 2021AGORA: Avatars in Geography Optimized for Regression Analysiscited by 205
  7. 2021EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devicescited by 139
  8. 2020Accurate 3D Hand Pose Estimation for Whole-Body 3D Human Mesh Estimationcited by 81

Built on by

Not cited yet.