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 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.



Challenge

For information about tracks, evaluation, and metrics, see 3DPW Challenge.

Paper submission is not mandatory (but encouraged) to participate in the challenge.

The three top performing methods (2 top performing methods in joint position accuracy, and top performing method on part orientation accuracy) will be invited to give a talk at the workshop.

Paper Submission

Submission Deadline July 23
Challenge Deadline July 23
Reviews Due August 8
Notification of Acceptance August 11
Workshop August 23
Camera Ready Submission September 14
Important Information:


Invited Speakers

...
Jitendra Malik
...
Dushyant Mehta

...
Georgios Pavlakos
...
Tony Tung
...
Gul Varol


Program

13:30 Welcome and introduction
13:40 Jitendra Malik
14:20 Dushyant Mehta
15:00 Georgios Pavlakos
15:40 Challenge Winner (Talk 1)
16:00 Tony Tung
16:40 Challenge Winner (Talk 2)
17:00 Challenge Winner (Talk 3)
17:20 Gul Varol


Challenge

Everyone can participate in the challenge! Submissions to the workshop are encouraged, but not mandatory to participate in the challenge.
Information about the challenge, evaluation metrics and protocols can be found at the 3DPW Challenge submission website. Below, you can find the video of the ECCV'18 paper associated with the 3DPW dataset:



Organizers

Special Thanks

We would like to thank Timo von Marcard, Dushyant Mehta, Ikhsanul Habibie, and Mohamed Omran for useful discussions on evaluation metrics and protocols for 3D Human Pose Estimation.
We also thank Meysam Madadi and Sergio Escalera for help and support setting up the challenge in Codalab.