Description

The number of research papers on 3D pose estimation, and in particular in un-controlled settings has dramatically increased recently. Most papers demonstrate performance qualitatively, showing images and the corresponding 3D body model or stick gure side by side. Quantitative evaluation is limited to indoor datasets such as H3.6M or Human-Eva, or outdoor datasets with recording volume like MuPoTs-3D. This changed with 3DPW (https://virtualhumans.mpi-inf.mpg.de/3DPW/), which constitutes the only dataset with accurate reference 3D poses in natural scenes (e.g., people shopping in the city, having coffee, or doing sports recorded with a moving hand-held camera). While researchers started using this dataset, the evaluation, protocols and sequences differ from paper to paper. This makes comparison of methods difficult. The purpose of this workshop and challenge is to standardize protocols and metrics so that researchers compare their methods in a consistent manner in future publications, ultimately to advance the state of the art in 3D human pose estimation in the wild. The tentative program consists in invited talks by Jitendra Malik and Kostas Daniilidis and the 3 top performing methods of the 3DPW-Challenge, and a poster session for workshop papers and invited relevant papers from the main conference.



Submission

Submission Deadline TBD
Reviews Due TBD
Notification of Acceptance TBD
Camera Ready Submission TBD
Workshop August 24
Important Information:


Invited Speakers

...
Jitendra Malik
...
Kostas Daniidilis


Program

13:30 Welcome and introduction
13:40 Jitendra Malik
14:20 Winner of Challenge 1
14:40 Winner of Challenge 2
15:00 Poster Session
16:00 Kostas Daniidilis
16:20 Invited Speaker 3
17:00 Winner of Challenge 3


Challenge

Information about the challenge and evaluation protocols will be posted here. Below, you can find the video of the ECCV'18 paper associated with the 3DPW dataset:



Organizers