Internship - 3D Infant Motion Estimation from RGB Video

Inria Montbonnot Montbonnot, France

About the position

Context

The internship will take place within the Kinetix team at Inria of Grenoble Alpes University. The student will be supervised by Felix Küper, Nikolas Hesse, and Sergi Pujades.

Assignment

Context

Recovering 3D human pose and shape from images or videos is a core problem in 3D vision. Recent foundation models for human mesh recovery (HMR), such as SAM 3D Body [1], estimate full-body meshes from a single image with impressive robustness. Video-based methods add temporal consistency and handle camera motion. Large synthetic datasets such as BEDLAM2 [2] have been key to training them, because they provide perfect 3D ground truth.
These models are trained almost exclusively on adults. Infants have different body proportions, poses, and appearance, and marker-based ground truth cannot be collected for them, so labeled data is scarce. Yet infant motion analysis has strong clinical value. The quality of spontaneous movement in the first months of life is an early indicator of neuromotor disorders such as cerebral palsy, and video-based markerless capture would make assessment possible at scale. Recent work [3] shows that fine-tuning SAM 3D Body on unlabeled infant video improves its predictions. However, it relies on pseudo-labels from another model, operates on single frames, and still reconstructs infants with an adult-shaped body model.
Internship
The goal of this internship is to improve the estimation of 3D infant motion from RGB video.
The work will include:
running and benchmarking state-of-the-art HMR methods, image-based and video-based, on infant videos, and analyzing their failure modes;
creating a large-scale synthetic video dataset of infants with exact 3D ground truth, as an important milestone toward fine-tuning. To our knowledge, no such dataset exists;
running, fine-tuning, and improving video-based HMR methods, and evaluating the gains on real infant videos.
Dataset generation and training will run on the Kinovis and GRICAD compute cluster.
The project combines 3D vision, synthetic data generation, deep learning, and large-scale experiments on an HPC cluster. A scientific publication is a realistic outcome.
What you will gain
Hands-on work with current frontier models
Experience in 3D vision and synthetic data generation
Experience with HPC
A real application with clinical impact
A potential publication
References
[1]
SAM 3D Body: Robust Full-Body Human Mesh Recovery
, Yang et al., CVPR 2026
[2]
BEDLAM2.0: Synthetic Humans and Cameras in Motion
, Tesch et al., NeurIPS 2025 (Datasets and Benchmarks)
[3]
Cross-Model Distillation of a Human-Pose Foundation Model from Unannotated Infant Video for Markerless 3D Pose Estimation
, Cotton et al., 2026 (arXiv preprint)

Main activities

Reading and analyzing advantages and disadvantages of related literature
Studying and preparing data
Implementing solutions for the problem
Evaluating the implemented solutions and existing works

Skills

Profile

We are looking for a highly motivated M2 student in Computer Science, Computer Vision, Machine Learning, Computer Graphics, Applied Mathematics, or a related field. Good programming skills in Python are required, as is experience with deep learning frameworks (PyTorch). Background in computer vision, 3D geometry, rendering, or human body models (SMPL-type) would be appreciated.

This listing was collected from a public source and is reproduced here for information only. Always confirm the details on the original posting before applying.
View the original posting

Similar positions