Direct human shape estimation by learning parametric model embeddings - Naver Labs Europe
loader image
20 December 2019
Meylan, France
Job Type
Start date
Spring 2020
5-6 months


Over the past few years, differentiable parametric models such as SMPL [1] for human bodies or MANO [2] for human hands have lead to significant progress in body/hand shape estimation from single images. In particular, several methods [3,4] leverage CNNs to directly regress SMPL/MANO parameters. These parametric models allow to control the shape by splitting the paremeters into camera pose parameters, shape parameters and pose parameters.
However, this expressive and meaningful space of the parameters might suffer from their design as some variables have significantly different statistics and impact on the output compared to some others. The goal of this internship is to learn a better space for direct regression of parametric models by CNNs. Further application of such parametric model embeddings could include human shape dynamic prediction [5].


Supervisor: Philippe Weinzaepfel


[1] SMPL: A skinned multi-person linear model. Loper et al. ACM Trans. Graphics 2015.
[2] Embodied Hands: Modeling and capturing hands and bodies together. Romero et al. ACM
Trans. Graphics 2017.
[3] Learning to reconstruct 3D human pose and shape via model-fitting in the loop. Pavlakos et
al. ICCV 2019.
[4] Delving Deep Into Hybrid Annotations for 3D Human Recovery in the Wild. Rong et al. ICCV
[5] Predicting 3D human dynamics from video. Zhang et al. ICCV 2019.

Required skills

– in pursuit of master or doctoral degree in a relevant field
– proven experience in python
– hands-on experience with deep learning frameworks
– high level of innovation and motivation
– communication skills in English

Application instructions

Please note that applicants must be registered students at a university or other academic institution and that this establishment will need to sign an 'Internship Convention' with NAVER LABS Europe before the student is accepted.

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.


NAVER LABS is a world class team of self-motivated and highly engaged researchers, engineers and interface designers collaborating together to create next generation ambient intelligence technology and services that are rich with the organic understanding they have of users, their contexts and situations.

Since 2013 LABS has led NAVER’s innovation in technology through products such as the AI-based translation app ‘Papago’, the omni-tasking web browser ‘Whale’, the virtual AI assistant ‘WAVE’, in-vehicle information entertainment system ‘AWAY’ and M1, the 3D indoor mapping robot.

The team in Europe is multidisciplinary and extremely multicultural specializing in artificial intelligence, machine learning, computer vision, natural language processing, UX and ethnography. We collaborate with many partners in the European scientific community on R&D projects.

NAVER LABS Europe is located in the south east of France in Grenoble. The notoriety of Grenoble comes from its exceptional natural environment and scientific ecosystem with 21,000 jobs in public and private research. It is home to 1 of the 4 French national institutes in AI called MIAI (Multidisciplinary Innovation in Ai) It has a large student community (over 62,000 students) and is a lively and cosmopolitan place, offering a host of leisure opportunities. Grenoble is close to both the Swiss and Italian borders and is the ideal place for skiing, hiking, climbing, hang gliding and all types of mountain sports.

Drop files here browse files ...
Are you sure you want to delete this file?