Command Palette
Search for a command to run...
Monet Nicolas ; Wee Dongyoon
Abstract
This technical report introduces our solution, MEEV, proposed to the EgoBodyChallenge at ECCV 2022. Captured from head-mounted devices, the datasetconsists of human body shape and motion of interacting people. The EgoBodydataset has challenges such as occluded body or blurry image. In order toovercome the challenges, MEEV is designed to exploit multiscale features forrich spatial information. Besides, to overcome the limited size of dataset, themodel is pre-trained with the dataset aggregated 2D and 3D pose estimationdatasets. Achieving 82.30 for MPJPE and 92.93 for MPVPE, MEEV has won theEgoBody Challenge at ECCV 2022, which shows the effectiveness of the proposedmethod. The code is available at https://github.com/clovaai/meev
Code Repositories
Benchmarks
| Benchmark | Methodology | Metrics |
|---|---|---|
| 3d-human-pose-and-shape-estimation-on-egobody | MEEV | Average MPJPE (mm): 82.3032 MPVPE: 92.9391 PA-MPJPE: 55.1292 PA-MPVPE: 62.9764 |
| 3d-human-pose-estimation-on-3dpw | MEEV | MPJPE: 81.74 |
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.