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.
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.
|Submission Deadline||July 23|
|Challenge Deadline||July 23|
|Reviews Due||August 8|
|Notification of Acceptance||August 11|
|Camera Ready Submission||September 14|
- All deadlines are 5 PM Pacific time.
- Paper submissions should follow the exact same guidelines of ECCV, 14 pages plus references.
- Submissions can be uploaded to the CMT: [not active yet]
- If you do not have one already, create an account for cmt3 and login.
- In case you are not directed to 3DPW submission, type 3DPW in the search box to find it.
- Accepted papers will be published in the proceedings of ECCV workshops.
|13:30||Welcome and introduction|
|15:40||Challenge Winner (Talk 1)|
|16:40||Challenge Winner (Talk 2)|
|17:00||Challenge Winner (Talk 3)|
ChallengeEveryone 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:
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.