Plenary Event
Monday Plenary Session
8 April 2024 • 13:30 - 15:15 CEST | Auditorium Schweitzer, Niveau/Level 0
13:30 – 13:40 hrs CEST
Welcome and Opening Remarks
13:40-13:45 hrs CEST
Speaker Introduction
13:45 - 14:30 hrs CEST
Future of optical system and lens design in the AI era
The arrival of ChatGPT, Google Bard, and other highly advanced artificial intelligence model show us just how brilliantly tasks can be reproduced by those engines. So, it's legitimate to wonder how our field (or any fields) might be affected in the future. We've already seen the beginnings of the possibilities, notably with LensNet [1], which provides optical designers with starting points for common cases; we can also study a solution space of certain type of lenses using deep learning [2]; and more recently, papers on the use of deep learning to simulate the entire chain of an optical system from object to final image processing, including tasks such as recognition. These latest end-to-end simulations have shown that in some cases, it is even necessary to redefine the optical optimization criteria to maximize certain computer tasks. In short, the computer doesn't necessarily need a good image in terms of MTF to perform its task. In this context, how the future will be affected or enhanced by these new AI approaches.
In this presentation, I will first give a brief history of how AI has impacted optical system design since 40 years. Then I will use examples to discuss the extraordinary acceleration in works over the past 5 years, the choices that have or haven't been made, and the importance of having access to source code from publications. Finally, I will conclude with some thoughts on what may or may not lie ahead, and how we can introduce these new technologies into the training of future optical system designers.
[1] Geoffroi Côté, Jean-François Lalonde, and Simon Thibault, "Deep learning-enabled framework for automatic lens design starting point generation," Opt. Express 29, 3841-3854 (2021).
[2] Geoffroi Côté, Yueqian Zhang, Christoph Menke, Jean-François Lalonde, and Simon Thibault, "Inferring the solution space of microscope objective lenses using deep learning," Opt. Express 30, 6531-6545 (2022).
Simon Thibault is head of the physics, engineering physics and optics department at Laval University and Immervision’s Principal Optical Designer working on cutting edge new method in lens design and applied research. SPIE and OSA Fellow, he is also the chair holder of the NSERC Industrial Research Chair in Optical Design supporting a world-class infrastructure for optical training (http://lrio.copl.ulaval.ca/) and sits on several international conference program committees at Optica, SPIE and IEEE. Particularly as Chair the International Optical Design Conference (IODC, 2021, 2023 in Quebec City).
He has authored over 300 scientific papers and holds more than 30 patents. His is an associate editor of Optics Express, Optical Engineering, member of the editorial board of Journal of Optics, and special section editors with Applied Optics and Optics Express. His research focuses on new emerging technologies such as AI in lens design, metasurface, and liquid surface for ground and space applications.
14:30 - 15:15 hrs CEST:
Freeform optics for illumination: past, present and future
Freeform optics for illumination, pioneered over 20 years ago, are now widely used to light up streets, automobiles, architecture and more. But many questions remain: Do we have good, accessible design methods, especially for extended sources? Do we have proven processes to estimate and specify tolerances, to ensure full production yield without overengineering? Do we fully understand diffractive structures on freeform surfaces? The talk discusses the progress of design and manufacturing methods over the last 30 years, shows the knowledge gaps we’re suffering from, and concludes with an outlook to a non-obvious but exciting new approach for coherent light: What happens when we combine freeform surfaces with scattering and spatial light modulation?
Julius Muschaweck, a German physicist, has been working on optical design for illumination for over twenty-five years. After a stay as Visiting Scholar at the University of Chicago with Prof. Roland Winston (well known as the originator of Nonimaging Optics), he co-founded and served as CEO of OEC, an optical-engineering-service-plus-research-institute, which pioneered freeform optics for illumination. Later, as Senior Principal Key Expert at OSRAM, he coordinated and educated the over 100 optical designers within OSRAM world-wide. He then joined ARRI, the leading movie camera and lamp head maker, as Principal Optical Scientist. Julius Muschaweck now works as an independent science and engineering consultant, providing illumination optics solutions to industry clients, teaching courses on illumination optics, and writing about the subject. He is the author of over 25 scientific papers, an SPIE tutorial book, and the inventor of over 50 patent applications. And he loves to go hiking with his wife and their dog.
Welcome and Opening Remarks
 |
Thierry Lépine
Institut d’Optique & Hubert Curien Lab (France) 2024 Symposium Chair |
13:40-13:45 hrs CEST
Speaker Introduction
 |
Tina Kidger
Kidger Optics Associates (United Kingdom) 2024 Symposium Chair |
 |
Marta C. de la Fuente
ASE Optics Europe (Spain) 2024 Symposium Chair |
13:45 - 14:30 hrs CEST
Future of optical system and lens design in the AI era
 |
Simon Thibault
Univ. Laval (Canada) |
The arrival of ChatGPT, Google Bard, and other highly advanced artificial intelligence model show us just how brilliantly tasks can be reproduced by those engines. So, it's legitimate to wonder how our field (or any fields) might be affected in the future. We've already seen the beginnings of the possibilities, notably with LensNet [1], which provides optical designers with starting points for common cases; we can also study a solution space of certain type of lenses using deep learning [2]; and more recently, papers on the use of deep learning to simulate the entire chain of an optical system from object to final image processing, including tasks such as recognition. These latest end-to-end simulations have shown that in some cases, it is even necessary to redefine the optical optimization criteria to maximize certain computer tasks. In short, the computer doesn't necessarily need a good image in terms of MTF to perform its task. In this context, how the future will be affected or enhanced by these new AI approaches.
In this presentation, I will first give a brief history of how AI has impacted optical system design since 40 years. Then I will use examples to discuss the extraordinary acceleration in works over the past 5 years, the choices that have or haven't been made, and the importance of having access to source code from publications. Finally, I will conclude with some thoughts on what may or may not lie ahead, and how we can introduce these new technologies into the training of future optical system designers.
[1] Geoffroi Côté, Jean-François Lalonde, and Simon Thibault, "Deep learning-enabled framework for automatic lens design starting point generation," Opt. Express 29, 3841-3854 (2021).
[2] Geoffroi Côté, Yueqian Zhang, Christoph Menke, Jean-François Lalonde, and Simon Thibault, "Inferring the solution space of microscope objective lenses using deep learning," Opt. Express 30, 6531-6545 (2022).
Simon Thibault is head of the physics, engineering physics and optics department at Laval University and Immervision’s Principal Optical Designer working on cutting edge new method in lens design and applied research. SPIE and OSA Fellow, he is also the chair holder of the NSERC Industrial Research Chair in Optical Design supporting a world-class infrastructure for optical training (http://lrio.copl.ulaval.ca/) and sits on several international conference program committees at Optica, SPIE and IEEE. Particularly as Chair the International Optical Design Conference (IODC, 2021, 2023 in Quebec City).
He has authored over 300 scientific papers and holds more than 30 patents. His is an associate editor of Optics Express, Optical Engineering, member of the editorial board of Journal of Optics, and special section editors with Applied Optics and Optics Express. His research focuses on new emerging technologies such as AI in lens design, metasurface, and liquid surface for ground and space applications.
14:30 - 15:15 hrs CEST:
Freeform optics for illumination: past, present and future
 |
Julius A. Muschaweck
JMO GmbH (Germany) |
Freeform optics for illumination, pioneered over 20 years ago, are now widely used to light up streets, automobiles, architecture and more. But many questions remain: Do we have good, accessible design methods, especially for extended sources? Do we have proven processes to estimate and specify tolerances, to ensure full production yield without overengineering? Do we fully understand diffractive structures on freeform surfaces? The talk discusses the progress of design and manufacturing methods over the last 30 years, shows the knowledge gaps we’re suffering from, and concludes with an outlook to a non-obvious but exciting new approach for coherent light: What happens when we combine freeform surfaces with scattering and spatial light modulation?
Julius Muschaweck, a German physicist, has been working on optical design for illumination for over twenty-five years. After a stay as Visiting Scholar at the University of Chicago with Prof. Roland Winston (well known as the originator of Nonimaging Optics), he co-founded and served as CEO of OEC, an optical-engineering-service-plus-research-institute, which pioneered freeform optics for illumination. Later, as Senior Principal Key Expert at OSRAM, he coordinated and educated the over 100 optical designers within OSRAM world-wide. He then joined ARRI, the leading movie camera and lamp head maker, as Principal Optical Scientist. Julius Muschaweck now works as an independent science and engineering consultant, providing illumination optics solutions to industry clients, teaching courses on illumination optics, and writing about the subject. He is the author of over 25 scientific papers, an SPIE tutorial book, and the inventor of over 50 patent applications. And he loves to go hiking with his wife and their dog.