Albert Murienne

Institut de Recherche Technologique B-com

Papers

Total Citations

H-Index

About

Albert Murienne is a researcher specializing in computer vision and deep learning, with a particular focus on 6 Degrees of Freedom (6DoF) object pose estimation — a critical challenge at the intersection of augmented reality and robotics. His work addresses one of the field's most demanding problems: accurately determining the precise 3D position and orientation of objects from single RGB-D images, even in cluttered real-world scenes and with limited training data. Murienne's most notable contribution, **L6DNet** (2020), introduced a lightweight hybrid pipeline combining data-driven and geometric approaches to achieve robust pose estimation with small datasets — a significant practical advancement given the scarcity of labeled 3D training data. This work has garnered 16 citations, reflecting its relevance to the robotics and AR communities. His follow-up work, **YOLOff** (2020), further pushed the boundaries by learning offset-based predictions for efficient and accurate 6DoF estimation in complex scenes. What distinguishes Murienne's research is his emphasis on practical deployability — designing systems that perform reliably under real-world constraints such as dataset limitations and scene clutter. His contributions offer valuable tools for researchers and engineers building next-generation robotic perception and augmented reality systems.