Learning Synthetic to Real Transfer for Localization and Navigational Tasks - Naver Labs Europe
loader image
4 October 2019
Meylan, France
Job Type
Start date
January-February 2020
5-6 months


Recent progresses in Artificial Intelligence led to a high interest in developing autonomous robots and equipping them with a human-level perception. Two critical abilities of any robot are to localize itself and to navigate in a complex environment. Deep neural networks allow localization methods and navigational policies be learned by supervised learning. Most sophisticated networks achieve high accuracy but require a massive amount of observations. Unfortunately, the ground truth labels are hard to obtain.

Simulation represents the most promising approach to resolve this dilemma and get a massive amount of annotated observations. However, the transfer of knowledge learned from simulation and synthetic data to real world environment remains a serious problem. The recent advances in the domain propose techniques of adaptation and generalization to facilitate such a transfer for some important sub-tasks, such as depth estimation and camera pose estimation. We therefore propose this research project aimed at developing techniques for transferring knowledge from synthetic to real world for the localization and navigational tasks. In particular, these techniques should account on specific geometric structure of the natural images in the real data, which is important for high-performing synthetic-to-real transfer.

We are looking for candidates motivated in research and innovation, in their 2nd year of Master's or equivalent degree in Computer Science, Computer Vision, or close domains.
Supervisors:  Tomi Silander, Boris Chidlovskii

Optional skills

The working knowledge of Python, C/C++ as well as the Deep / Reinforcement Learning

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?