Full Body 3D Human Pose in the Wild - Internship - Naver Labs Europe
NAVER LABS Europe
Published
19 November 2020
Location
Meylan, Grenoble, France, France
Category
Start date
ASAP
Duration
6 months

Description

3D human pose estimation, e.g. [A,B] consists in detecting the 3D location of human joints from natural images. It has become a key element of various tasks, ranging from teaching robots to reproduce human actions to avatar animation for VR and AR, and is an active research topic in the community. This internship targets the problem of 3D human pose estimation in video sequences of immobile people. Recent findings at NaverLabs Europe [C] have shown that it is possible to exploit the immobility of the subjects in the sequences to extract accurate 3D poses. The objective of this internship is to 1. improve the level of details of such poses, by adding hands and faces keypoints as in [D], and 2. use them to evaluate and improve 3D pose estimation methods, targeted at in-the-wild applications. This would involve initial literature review and familiarization with Naver internal tools, teams and code. In a first step, the intern will be asked to investigate the possible addition of the hands and facial details in the existing estimation procedure. Later, the intern will be free to record sequences on his own, and possibly use them to design, train and/or evaluate pose estimation models, for publication in a top-tier conference or journal.

Required skills

Python
Experience with PyTorch and SMPL or SMPL-X body models is a plus

References

[A] 3D human pose estimation in video with temporal convolutions and semi-supervised training, D. Pavllo, C. Feichtenhofer, D. Grangier, M. Auli, in CVPR 2019
[B] DOPE: distillation of part experts for whole-body 3D pose estimation in the wild, P. Weinzaepfel, R. Brégier, H. Combaluzier, V. Leroy, G. Rogez, in ECCV 2020
[C] SMPLy benchmarking 3D human pose estimation in the wild, V. Leroy, P. Weinzaepfel, R. Brégier, H. Combaluzier, G. Rogez,  in 3DV 2020
[D] Expressive Body Capture: 3D Hands, Face, and Body from a Single Image, G. Pavlakos, V. Choutas N. Ghorbani, T. Bolkart, A. Osman, D. Tzionas, M.J. Black, in CVPR 2019

Application instructions

You can apply for this position online. Don't forget to upload your CV and cover letter before you submit. Incomplete applications will not be accepted.

Due to the changing travel restrictions related to COVID-19, it may not be possible to host candidates from certain regions. This will depend on the conditions at the specific starting date of the internship.

About NAVER LABS

NAVER LABS Europe has full-time positions, PhD and PostDoc opportunities throughout the year which are advertised here and on international conference sites that we sponsor such as CVPR, ICCV, ICML, NeurIPS, EMNLP etc.

NAVER LABS Europe is an equal opportunity employer.

NAVER LABS are in Grenoble in the French Alps. We have a multi and interdisciplinary approach to research with scientists in machine learning, computer vision, artificial intelligence, natural language processing, ethnography and UX working together to create next generation technology and services that deeply understand users and their contexts.

Apply to this internship
Drop files here browse files ...
Drop files here browse files ...
Drop files here browse files ...
Captcha

Related Jobs

25 November 2020
16 November 2020
Learning to grasp as a human demonstration - Internship   Meylan, Grenoble, France, France
16 November 2020
9 November 2020
5 November 2020
Are you sure you want to delete this file?
/