Research Engineer: Detailed riggable humans from multi-view video

Inria; France; Hybride; EUR 2 600 - 3 600; Plein temps

Avantages offerts par ce poste

Partial transport reimbursement

7 weeks leave + RTT days + exceptional

90 days teleworking per year

Professional equipment available

Social, cultural and sports events

Vocational training

Complementary health insurance

Résumé du poste

Inria Grenoble is seeking a Research Engineer to advance detailed, riggable human models from multi-view videos. The role sits in the Morpheo team, focusing on novel rigging approaches and high-fidelity animation from image streams.

You will build on multi-view reconstruction work, explore dataset enhancements, and deliver a proof-of-concept implementation in collaboration with research advisers. A graduate degree is expected.

Qualifications

• Graduate degree or equivalent required.
• Master 2 also valued.

Responsabilités

• Establish a more complete bibliography of relevant methods.
• Propose methodological and architectural innovations for rigging a detailed animated model from images.
• Propose and discuss dataset enhancements to improve training.
• Demonstrate a proof of concept implementation with team advisers.
• Identify existing datasets relevant for evaluation.

Connaissances

AI/ML background

Python

PyTorch

Mathematical formalization

Scientific curiosity

Formation

Graduate degree or equivalent

Master 2

Outils

Python

PyTorch

Description du poste

Research Engineer: Detailed riggable humans from multi-view video

Level of qualifications required : Graduate degree or equivalent

Other valued qualifications : Master 2

Fonction : Temporary scientific engineer

About the research centre or Inria department

The Inria Grenoble research center groups together almost 600 people in 27 research teams and 8 research support departments.

Staff is present on three campuses in Grenoble, in close collaboration with other research and higher education institutions (University Grenoble Alpes, CNRS, CEA, INRAE, …), but also with key economic players in the area.

Inria Grenoble is active in the fields of high-performance computing, verification and embedded systems, modeling of the environment at multiple levels, and data science and artificial intelligence. The center is a top-level scientific institute with an extensive network of international collaborations in Europe and the rest of the world.

Context

Within the framework of a partnership

• The project's findings will contribute to a follow up 4-year BPI transfer project (Banque Publique d'investissement)with a consortium of French production companies. The project is liable to begin during this contract period, with discussions with involved partners

Assignment

Context

Many works nowadays provide solutions for the avatarization process, i.e. obtaining a 3D, animatable model from one or several images. This is a very hard problem as shape fidelity, animatability, fast computation time and low number of required input cameras are all desirable, but hardly realizable simultaneously. For example, obtaining plausible models from a single camera video is nowadays feasable, but often at the cost of shape quality due to the use of low-parametric models such as SMPL. Using many videos for redundancy can allow to acquire more detail, but at the expense of computation speed. And all this detail needs to be animatable, which gets more complex with the scale of detail (i.e. millimeter shape with only a human kinematic rig), again putting a burden on the model and its computation time.

Mission

In recent years the Morpheo team has come up with very precise multi-view reconstruction approaches [1].
In this project, we wish to examine the problem of animating this type of detailed model and rig it, by exploring the stream of recent methods.

Main activities

During his activity, the candidate is expected to tackle the following tasks

• establish a more complete bibliography of relevant methods based on the initial suggested references
• propose and discuss likely and realizable methodological and architecture innovations / reparametrizations that allow to rig and estimate a detailed animated model from images, grounded in this existing work
• propose and discuss dataset enhancements that would enrich the training toward better performance for these tasks
• demonstrate a proof of concept implementation of an envisioned solution discussed with team research advisers
• identify existing datasets that are relevant for comparative evaluation of performance of his proposals. In-house datasets such as 4DHumanOutfit[2]

Benefits package

• Partial reimbursement of public transport costs
• Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
• Possibility of teleworking (90 days / year) and flexible organization of working hours
• Professional equipment available (videoconferencing, loan of computer equipment, etc.)
• Social, cultural and sports events and activities
• Access to vocational training
• Complementary health insuranceunder conditions

Remuneration

From 2,692 € (depending on experience and qualifications).

• Theme/Domain :Vision, perception and multimedia interpretation
  Scientific computing(BAP E)

Defence Security :

This position is likely to situated in a restricted area (ZRR), as defined in Decree No. 2011-1425 relating to the protection of national scientific and technical potential (PPST).Authorisation to enter an area is granted by the director of the unit, following a favourable Ministerial decision, as defined in the decree of 3 July 2012 relating to the PPST. An unfavourable Ministerial decision in respect of a position situated in a ZRR would result in the cancellation of the appointment.

Recruitment Policy :

As part of its diversity policy, all Inria positions are accessible to people with disabilities.

The candidate is expected to have skills in any or all of the following domains

• mathematical formalization
• AI / machine learning / deep learning background
• some Python / PyTorch experience
• scientific curiosity, taste and autonomy in explorative tasks and problems

References

[1] Toussaint, Briac and Thomas, Diego and Franco, Jean-Sébastien
ProbeSDF: Light Field Probes For Neural Surface Reconstruction, Proceedings of the Computer Vision and Pattern Recognition Conference, 2025

[5] Zhouyingcheng Liao and Vladislav Golyanik and Marc Habermann and Christian Theobalt
VINECS: Video-based Neural Character Skinning
Computer Vision and Pattern Recognition (CVPR), 2024

[6] Sapiens, Foundation for Human Vision Models
Rawal Khirodkar · Timur Bagautdinov · Julieta Martinez · Su Zhaoen · Austin James Peter Selednik . Stuart Anderson . Shunsuke Saito ECCV 2024

[8] Yushuo Chen, Zerong Zheng, Zhe Li, Chao Xu, Yebin Liu,
MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos ECCV 2024

[9] Decai Chen, Brianne Oberson, Ingo Feldmann,
Oliver Schreer, Anna Hilsmann, Peter Eisert Adaptive and Temporally Consistent Gaussian Surfels for Multi-view Dynamic Reconstruction WACV 2025 Oral

About Inria

Inria, the French national institute for research in digital science and technology, supports the French government in national research and innovation strategies in digital field, acting as Digital Programs Agency. Inria leads over 300 research and innovation projects with its 3,500 scientists, engineers, and support staff, in partnership with universities and the digital ecosystem (businesses, entrepreneurs, and public stakeholders). Together, we explore strategic fields such as artificial intelligence, cybersecurity, quantum computing, cloud technologies, digital transformation in healthcare, digital twins, and digital technologies for defence. We develop practical solutions such as software, tech startups, partnerships with national companies, and cutting-edge training programmes. Our goal is to drive scientific, technological, and industrial excellence to ensure France’s digital sovereignty.