Research Engineer: Detailed riggable humans from multi-view video

Inria, the French national research institute for the digital sciences; France; Hybride; EUR 26 000 - 35 000; Plein temps

Avantages offerts par ce poste

Transport partiellement remboursé

7 semaines de congés + RTT

Télétravail (90 jours/an)

Équipement informatique fourni

Événements et activités sociales

Formation professionnelle

Assurance santé complémentaire

Résumé du poste

Inria, the French national research institute for the digital sciences, au sein de l’équipe Morpheo, recherche un(une) chercheur(se) pour explorer des méthodes de reconstitution multi-vues et les rendre exploitables pour l’animation de modèles détaillés.

Le candidat doit posséder des compétences en IA/ML, une expérience en Python/PyTorch, et une forte curiosité scientifique avec autonomie dans des tâches exploratoires.

Qualifications

• Compétences en IA / machine learning / deep learning.
• Expérience en Python / PyTorch.
• Curiosité scientifique et autonomie dans les tâches exploratoires.

Responsabilités

• Établir une bibliographie plus complète des méthodes pertinentes.
• Proposer des innovations méthodologiques et reparamétrisations pour rigging et estimation d’un modèle détaillé à partir d’images.
• Proposer et discuter des enrichissements de jeux de données pour améliorer l’entraînement.
• Réaliser une preuve de concept d’une solution envisagée avec les conseillers de l’équipe.
• Identifier des jeux de données pertinents pour l’évaluation comparative.

Connaissances

AI / ML / DL

Python / PyTorch

Math formalization

Autonomie

Curiosité scientifique

Description du poste

Inria, the French national research institute for the digital sciences

Organisation/Company Inria, the French national research institute for the digital sciences Research Field Computer science Researcher Profile Recognised Researcher (R2) Leading Researcher (R4) First Stage Researcher (R1) Established Researcher (R3) Application Deadline 25 Oct 2026 - 00:00 (UTC) Country France Type of Contract Temporary Job Status Full-time Hours Per Week 38.5 Offer Starting Date 1 Nov 2026 Is the job funded through the EU Research Framework Programme? Not funded by a EU programme Reference Number 2026-10518 Is the Job related to staff position within a Research Infrastructure? No

Offer Description

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

Context

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.

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]

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

Languages FRENCH Level Basic

Languages ENGLISH Level Good

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

Additional Information

• 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

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