Awarded work “High-fidelity 3D Hand Modelling, Detection and Reconstruction in world-coordinates” presented at EMVA Business Conference in Rome.
Next conference 2026 will take place in Stockholm.

Rome, Italy, May 27^th, 2025. The EMVA Young Professional Award 2025 goes to Dr. Rolandos Alexandros Potamias for his work “High-fidelity 3D Hand Modelling, Detection and Reconstruction in world-coordinates”. The awardee was announced on 23 May during the 23th EMVA Business Conference in Rome, where he also had the opportunity to present his work as part of the regular conference program. Rolandos Alexandros Potamias is a postdoctoral researcher in 3D Computer Vision at the Department of Computing of Imperial College London in United Kingdom, focusing on perceiving and modelling humans. Rolandos holds a MEng from the School of Electrical and Computer Engineering in National Technical University of Athens. He obtained his PhD degree from Imperial College London under the supervision of Stefanos Zafeiriou with the thesis entitled “Advances of graph neural networks for 3D shape learning and analysis”. Rolandos’ current research efforts focus on building foundational embodied AI for open-world robots.

Awarded Work: High-fidelity 3D Hand Modelling, Detection and Reconstruction in World-coordinates
Given their power to express human behaviour and interact with objects, hands present a very important, but still challenging to model component of the human body. The significance of hand modelling can be further amplified considering its social benefit amongst deaf and hard-of-hearing communities. Currently, most of the hand modelling methods rely on low polygon hand models that fail to capture the intricate details of the hands, making real-world AR/VR applications extremely challenging. Apart from its low polygon count, current hand models are trained using limited subjects, which not only prohibits their expressive power but also imposes unnecessary shape reconstruction constraints on 3D hand pose estimation methods. Moreover, hand appearance remains almost unexplored and neglected from the majority of hand reconstruction methods.

The awarded research can be divided in three main components: i) hand shape modelling, ii) hand detection and iii) 3D hand reconstruction. To achieve highly detailed 3D hand reconstruction, Potamias’ developed a large-scale model of the human hand, called Handy, modelling both shape and appearance, composed of over 1200 subjects with large diversity in age, gender, and ethnicity, enabling accurate reconstruction of out-of-distribution samples. Following this work, Potamias’ introduced WiLoR, a data-driven transformer-based pipeline for efficient and real-time multi-hand detection and 3D reconstruction from in-the-wild images. The developed model can efficiently detect and estimate the hand shapes and poses from images containing multiple hands. To enable motion modelling of the hands in the world-space, especially from egocentric wearable camera settings where hands and camera are continuously in motion, Potamias’ developed HaWoR, a SLAM-based hand motion reconstruction model. HaWoR decouples the task of 3D world-coordination hand motion reconstruction in two steps; reconstructing the hand motion in the camera space, and estimating the camera trajectory in the world coordinate system.

The technologies developed from Potamias’ research have received commercial attention and can further advance the various industrial applications ranging from augmented and virtual reality (AR/VR) and virtual try-on to embodied AI and robot-learning.

About the EMVA Young Professional Award
The EMVA Young Professional Award is an annual award to honor the outstanding and innovative work of a student or a young professional in the field of machine vision or image processing. It is the goal of the European Machine Vision Association EMVA to further support innovation in the machine vision industry, to contribute to the important aspect of dedicated machine vision education and to provide a bridge between research and industry. With the annual Young Professional Award the EMVA intends to specifically encourage students to focus on challenges in the field of machine vision and to apply latest research results and findings in computer vision to the practical needs of the industry. The Award winner is presented during the EMVA Business Conference.

Location of next EMVA Business Conference 2026
Traditionally, at the end of the conference it was announced in which city the next, 24^th EMVA Business Conference will take place. The machine vision industry will meet from 18 – 20 June, 2026 in Stockholm/Sweden.

—

Photo (From left to right): EMVA Board Member Petra Thanner; EMVA Young Professional Award 2025 winner Dr. Rolandos Alexandros Potamias; EMVA President Dr. Chris Yates;
Picture source: EMVA

Three keynote speeches on the topic of “AI-based image processing is changing logistics”.

Barcelona, 24 February 2025. Machine vision plays a decisive role in the optimization of logistics processes. At this year’s LogiMAT, three keynote speakers will show how AI and machine vision can optimize logistics processes at the EMVA expert forum “AI-based machine vision is changing logistics” on Tuesday, March 11 from 3 pm. – 3.50 pm. in the LogiMAT Arena, Atrium, East Entrance:

Dr. Michael Suppa, CEO, Roboception GmbH will be speaking on the topic of “AI-based Perception of Unknown Flexible Items”. The presentation by Shane MacNamara, Senior Vice President Research & Development, SICK AG is entitled “AI: Game-Changer in Image-Based Solutions for the Logistics Industry”; and Adrian Vich, Application Engineer, Stemmer Imaging ES will present on the topic of “Revolutionizing Efficiency and Precision Across Logistics Operations”. The expert forum will be moderated by Arndt Bake EMVA Treasurer and General Manager GTM EMEA, Basler AG.

The event will be simultaneously translated and is free of charge for LogiMAT visitors.

International experts are invited to join the ISO-TC42-Working Group 28.

Barcelona/Spain, November 22nd, 2024. Based on the positive and ongoing evolution towards more and more matured applications of vision technologies, in specific cameras and image sensors, the EMVA Board of Directors, representing the association’s members, has decided to lift the EMVA 1288 Standard up to an international standardization level. Consequently in 2023 the EMVA proposed the EMVA 1288 Standard to become an ISO Standard. In October 2024 the item proposal got accepted by the ISO Technical Committee 42 ‘Photography’ and the specific working group WG 28 has been founded and initiated its work. International experts are invited to bring in their expertise by joining the ISO-TC42-WG28.

Standards are backbone of machine vision industry
“Establishing international standards has been and will be crucial for the successful application of vision technologies not only in the industrial world but increasingly also in logistics, traffic, medical and several other user segments”, says EMVA General Manager Thomas Lübkemeier. Already in 2005, the first module of the EMVA 1288 Standard was officially released by the members and contributors of the EMVA hosted working group. Meanwhile the ‘Standard for Measurement and Presentation of Specifications for Machine Vision Sensors and Cameras’ continuously has been further developed and the Release 4.1 is close to be finalized. “The EMVA 1288 Standard today is well accepted and especially camera producers worldwide apply the standard in their production lines and quality assurance departments”, Thomas Lübkemeier confirms.

Experts invited to contribute
The ISO – International Organization for Standardization is a network of 172 national standards bodies. ISO members are the foremost standards organizations in their country and there is only one member per country. Each member represents ISO in its country and is entitled to nominate experts into the various ISO working groups.
Experts motivated to share their expertise to the ISO-24942 initiative may find more details on how to join at EMVA’s website and of course via the official ISO channels.

Focal Topic addresses Challenges and Chances in Computer Vision for Human-Machine Interaction

Barcelona/Spain, October 23rd, 2024. Hosted by the EMVA, the seventh European Machine Vision Forum on November 7 – 8 in Mulhouse, France, once again brings together machine vision experts from academia and industry for mutual exchange in a unique setting. The on-site host this year is École Nationale Supérieure d’Ingénieurs Sud-Alsace (ENSISA) of the Université de Haute-Alsace.

This time the focal topic is “Challenges and Opportunities in Computer Vision for Human-Machine Interaction”. The Chair of the European Machine Vision Forum, Professor Michael Heizmann, explains the intention behind the choice of topic: “While machine vision often focuses on the automation of monitoring, control and inspection tasks without human intervention, this year’s focus is on integrating humans as part of an overall system. This is relevant in many application areas, e.g. for assembly tasks in industry, but also when driving vehicles or playing computer games. Some technical issues are relevant in all of these domains, such as the choice of suitable sensor technology, the selection and parameterization of image processing methods and dealing with the always variable appearance of people. Issues such as the consideration of personal rights also often play an important role. At the forum, such aspects will be addressed in presentations and poster contributions. In addition, current research results and new applications in the entire field of machine vision will be presented.”

The first keynote lecture of the event is titled “Optical Measurements: From the Laboratory to Industry” and will be given by Jean-Pierre Chambard, HOLO3 Research Centre, Saint-Louis, France. The afternoon session of the first conference day will be opened by the second keynote speaker Maria-Theresa Licka of MAIMY and University of Kaiserslautern, Germany talking about “Machine Vision Solutions on Mobile Devices – Scaling Human-Machine Interaction”.

In his keynote talk on the second day of the event Christian Daul, CRAN, University of Lorraine and CNRS, Nancy, France will talk about “Improving Endoscopic Data Acquisition and Interpretation using 2D and 3D Mosaicing Algorithms for Poor Image Content”.

In addition to that, more than a dozen top-notch presentations will be given by representatives from industry and academia highlighting various aspects of the focal topic “Challenges and Chances in Computer Vision for Human-Machine Interaction”.

For more information on the forum, visit www.european-forum-emva.org.