Internship: Recovering 3D Hand–Object Interaction from Images F/M

About NAVER LABS Europe

NAVER LABS Europe is part of the R&D division of NAVER, Korea’s leading Internet portal and a global tech company with a range of services that include search, commerce, content, fintech, robotics and cloud.

The position

We are looking for a strong MSc student to join our effort in the detailed 3D reconstruction of hand–object interactions. This internship will be co-supervised by Philippe Weinzaepfel and Gregory Rogez, and Dimitris Tzionas from the University of Amsterdam is also likely to be involved.

Humans grasp and manipulate objects with their hands to perform everyday tasks. To enable computers and intelligent systems (such as robots) to understand our actions, we need algorithms for 3D visual perception, i.e. for reconstructing hands and objects in 3D from camera images.

However, this is a challenging task. 3D inference from 2D images is highly ill-posed, hands tend to be small and blurry, and the hand often occludes the object (and vice versa), leading to missing visual information. Consequently, this is a hot research topic for both academia and the tech industry. The following recent datasets provide excellent resources for progress in the field (in alphabetic order):

• GRAB dataset:  https://grab.is.tue.mpg.de;
• HOGrasp dataset:  https://hograspnet2024.github.io;
• SHOWMe dataset:  https://europe.naverlabs.com/research/showme.

However, these datasets are captured in controlled settings. The challenge is to train strong models on them so that they generalize out of distribution, i.e., to images taken in uncontrolled environments (such as internet images or images captured by autonomous robots).

About the research team

In the Vision group, we conduct research to enable robots to understand and interact with their environment through advanced perception systems. We focus on visual perception, a fundamental capability for any intelligent system designed to engage with the world. Robots must perceive the structure, objects, and people in their surroundings to build a deeper understanding of their environment and effectively perform assigned tasks. Our research combines 3D vision, visual representation learning, self-supervised learning, and human behavior understanding to develop AI components that help robots navigate in 3D environments, detect and interact with surrounding objects and people, and continuously adapt when deployed in new environments.

What we're looking for

• A candidate enrolled in an MSc program, aiming to pursue a PhD afterwards, potentially in collaboration with the University of Amsterdam
• Strong programming skills and hands-on experience with PyTorch
• Background in computer vision, 3D representations, and deep learning

What we offer

• We foster a collaborative environment dedicated to ambitious, multidisciplinary projects that translate advanced research into impactful, real-world solutions, supported by 30+ years of experience in AI and related fields.
• Flexible work/life balance.

• We are an equal opportunity employer that hires based on skills, experience, and merit. We foster an inclusive and diverse workplace where all qualified candidates are considered fairly, regardless of background.

• We’re based in Meylan, close to Grenoble, a city that offers the perfect balance of urban life, cutting-edge research and technology, and spectacular mountain landscapes that provide countless opportunities to relax, recharge, and enjoy the outdoors.

All applications will be carefully considered, even if not all required skills are met. We value diverse backgrounds and the potential of each candidate, and we offer training to support the development of necessary skills.

NAVER LABS, co-located in Korea and France, is the organization dedicated to preparing NAVER’s future. Scientists at NAVER LABS Europe are empowered to pursue long-term research problems that, if successful, can have significant impact and transform NAVER. We take our ideas as far as research can to create the best technology of its kind. Active participation in the academic community and collaborations with world-class public research groups are, among others, important ways to achieve these goals. Teamwork, focus and persistence are important values for us.

 When applying for this position online, please don't forget to upload your CV and cover letter. Incomplete applications will not be considered.

NAVER LABS Europe is subject to French jurisdiction requiring organisations to stipulate that a job/internship is open to both women and men. None of our jobs/internships are gender specific.

References

• HOSt3R: Keypoint-free Hand-Object 3D Reconstruction from RGB images. Swamy et al. ICCVW 2025
• Reconstructing Hand-Held Objects in 3D. Wu et al. arXiv 2024
• Hand-held Object Reconstruction from RGB Video with Dynamic Interaction. Jiang et al. CVPR 2025

Réf: 1edd9dbc-66cb-4e90-a607-be63d92f6805