Immersive & Medical Technologies

Augmented reality is upending many industrial sectors by offering a new way to perceive the environment.

Labo bcom - technologies immersives
© Fred Pieau
Healthcare applications are one promising example.

With its expertise in computer vision, pose estimation, and 3D visualization, the Immersive & Medical Technologies lab designs components and platforms to augment the experiences of professionals and strengthen their effectiveness, particularly through augmented reality and virtual reality, in fields like industry and health. Users are at the heart of its thinking and its work, from the definition of needs to the testing of developed technologies. In the field of health care, the lab works with its medical partners on key technologies like image processing and medical videos, connectivity, and interoperability.

products & services
Dicom Family - teaser produit - bcom DICOM family

Interoperability, anonymization, and standardization

Annotate - teaser produit - bcom b<>com Annotate

A surgical workflow editor and analytics tool

scientific publications


MES-loss: Mutually Equidistant Separation Metric Learning Loss Function

Deep metric learning has attracted much attention in recent years due to its extensive applications, such as clustering and image retrieval. Thanks to the success of deep learning (DL), many deep metric learning (DML) methods have been proposed. Neural networks (NNs) utilize DML loss functions to learn a mapping function that maps samples into a highly discriminative low-dimensional feature space…

read the publication


Multi-stage RGB-based Transfer Learning Pipeline for Hand Activity Recognition

First-person hand activity recognition is a challenging task, especially when not enough data are available. In this paper, we tackle this challenge by proposing a new low-cost multi-stage learning pipeline for firstperson RGB-based hand activity recognition on a limited amount of data. For a given RGB image activity sequence, in the first stage, the regions of interest are extracted using a pre…

read the publication


L6DNet: Light 6 DoF Network for Robust and Precise Object Pose Estimation with Small Datasets

Estimating the 3D pose of an object is a challenging task that can be considered within augmented reality or robotic applications. In this paper, we propose a novel approach to perform 6 DoF object pose estimation from a single RGB-D image. We adopt a hybrid pipeline in two stages: data-driven and geometric respectively. The data-driven step consists of a classification CNN to estimate the object…

read the publication


Efficient Multi-stream Temporal Learning and Post-fusion Strategy for 3D Skeleton-based Hand Activity Recognition

Recognizing first-person hand activity is a challenging task, especially when not enough data are available. In this paper, we tackle this challenge by proposing a new hybrid learning pipeline for skeleton-based hand activity recognition, which is composed of three blocks. First, for a given sequence of hand’s joint positions, the spatial features are extracted using a dedicated combination of…

read the publication