Tuesday 19 January 2021
PLENARY: Deep Internal Learning—Deep Learning with Zero Examples
Session Chair: Charles Bouman, Purdue University (United States)
10:00 – 11:10
Plenary Room
Deep internal learning—Deep learning with zero examples
Michal Irani, Professor in the Department of Computer Science and Applied Mathematics at the Weizmann Institute of Science (Israel)
Michal Irani is a professor at the Weizmann Institute of Science. Her research interests include computer vision, AI, and deep learning. Irani's prizes and honors include the Maria Petrou Prize (2016), the Helmholtz “Test of Time Award” (2017), the Landau Prize in AI (2019), and the Rothschild Prize in Mathematics and Computer Science (2020). She also received the ECCV Best Paper Awards (2000 and 2002), and the Marr Prize Honorable Mention (2001 and 2005).
11:10 – 11:40 SESSION BREAK: Join speakers in the EI2021 Discord Voice Channel corresponding to the color of the room in which the session occurs or join an Open Discord Channel of your choice. After a plenary, join the Plenary Discord Voice Channel.
KEYNOTE: Sensor Design I
Moderator: Jon McElvain, Dolby Laboratories (United States)
Session Chair: Arnaud Peizerat, CEA (France)
11:40 – 13:00
Blue Room
11:40ISS-089
KEYNOTE: Deep-trench isolation: The holy grail for image sensors?, Albert Theuwissen1,2; 1Harvest Imaging (Belgium) and 2TU Delft (the Netherlands)
Keynote speaker Albert Theuwissen received a degree in electrical engineering and his PhD from the Catholic University of Leuven (Belgium, 1977 and 1983, respectively). In 1983 he joined Philips Research Labs (the Netherlands) and in 2002 he started working for DALSA. His whole career he was involved in R&D of solid-state image sensors. He issued several patents and he is author or co-author of more than 240 technical papers, including a textbook "Solid-State Imaging with Charge-Coupled Devices". He acted as general chairman of the International Image Sensor Workshop in ’97, ’03, ‘09, and ’15, and as International Technical Program Chair of the ISSCC2010. In 2001, he became part-time professor at the Delft University of Technology, the Netherlands. He left DALSA in 2007, and founded Harvest Imaging. Since then he is fully focusing on training, teaching, and consulting in the field of solid-state imaging technology. In 2011 he received the Electronic Imaging of the Year Award and in 2017 he was elected as president of the International Image Sensor Society.
12:20
Roundtable with Albert Theuwissen
12:40ISS-090
A 64M CMOS image sensor using 0.7µm pixel with high FWC and switchable conversion gain (Invited), Jay Jung, Omnivision Technologies, Inc. (United States)
Since 2016, invited speaker Jay Jung has been a senior staff process integration engineer at Omnivision Technologies, Inc. Prior to this he was a TCAD manager and senior pixel engineer with Samsung from 2011-2016. He obtained his PhD in physics from Ohio State University, and his MS and BS in physics from Hanyang University, South Korea.
CONFERENCE INTERACTIVE POSTERS, DEMONSTRATIONS, AND BREAK
13:00 – 13:30
see below for location
Posters and/or Demonstrations presented live during this break are related to any of the conferences held today. Zoom links to visit the posters and/or demonstrations are found on the home page of the Symposium Portal. We invite you to visit with the presenters in the designated Zoom or meet with other attendees in Discord.
3DIA-069
ZOOM A — 3DIA POSTER: 3D shape estimation for smooth surfaces using double mirror system, Yin Wang1, Davi He2, Zillion Lin2, George Chiu1, and Jan Allebach1; 1Purdue University (United States) and 2SunValley Tek (China)
ISS-070
ZOOM B — ISS POSTER: An ultra-low-cost large-format wireless IoT camera, Henry Dietz and Paul Eberhart, University of Kentucky (United States)
MOBMU-075D
ZOOM C — MOBMU DEMO: "Perceptually optimized ABR ladder generation for web streaming", Yuriy Reznik, Karl Lillevold, and Rahul Vanam, Brightcove, Inc. (United States)
In the MOBMU demo, augmenting the oral presentation of the same title, Yuriy Reznik will show Brightcove context-aware encoping (CAE) technology.
KEYNOTE: Depth Sensing
Session Chair: Jon McElvain, Dolby Laboratories (United States)
Moderator: Arnaud Peizerat, CEA (France)
13:30 – 14:30
Blue Room
13:30ISS-087
KEYNOTE: 2D, or not 2D, that is the question: How 3D-stacking is shaping the future of SPAD image sensors, Edoardo Charbon, École Polytechnique Fédérale de Lausanne (Switzerland)
Keynote speaker Edoardo Charbon (SM’00, F’17) received the Diploma from ETH Zurich, an MS from the University of California at San Diego, and his PhD from the University of California at Berkeley (1988, 1991, and 1995, respectively), all in electrical engineering and EECS. He has consulted with numerous organizations, including Bosch, X-Fab, Texas Instruments, Maxim, Sony, Agilent, and the Carlyle Group. He was with Cadence Design Systems from 1995 to 2000, where he was the architect of the company's initiative on information hiding for intellectual property protection. In 2000, he joined Canesta Inc., as the chief architect, where he led the development of wireless 3-D CMOS image sensors. Since 2002 he has been a member of the faculty of EPFL, and has been a full professor since 2015. From 2008 to 2016 he was with Delft University of Technology as chair of VLSI design. Charbon has been the driving force behind the creation of deep-submicron CMOS SPAD technology, which is mass-produced since 2015 and is present in telemeters, proximity sensors, and medical diagnostics tools. His interests span from 3-D vision, LiDAR, FLIM, FCS, NIROT to super-resolution microscopy, time-resolved Raman spectroscopy, and cryo-CMOS circuits and systems for quantum computing. He has authored or co-authored more than 400 papers and two books, and he holds 23 patents. Charbon is a distinguished visiting scholar of the W. M. Keck Institute for Space at Caltech, a fellow of the Kavli Institute of Nanoscience Delft, a distinguished lecturer of the IEEE Photonics Society, and a fellow of the IEEE.
14:10
Roundtable with Edoardo Charbon
14:30 – 18:00 Break in program to accommodate time zones.
Sensor Design II
Moderator:
Jon McElvain, Dolby Laboratories (United States)
Session Chair:
Rihito Kuroda, Tohoku Univ. (Japan)
18:00 – 19:15
Blue Room
18:00
Conference Introduction
18:15ISS-091
A low-voltage 0.7 µm pixel with 6000 e- full-well capacity for a low-power CMOS image sensor, Seung-Wook Lee, Seungwon Cha, Dongyoung Jang, Mihye Kim, Haewon Lee, Nakyung Lee, Seonok Kim, Kwanyoung Oh, Daehyung Lee, SeungHan Hong, Hana Lee, Sunghoon Oh, Donghyuk Park, Yitae Kim, and JungChak Ahn, Samsung Electronics DS (Republic of Korea)
18:35ISS-092
A proposal of analog correlated multiple sampling with high density capacitors for low noise CMOS image sensors, Shunta Kamoshita, Manabu Suzuki, Rihito Kuroda, and Shigetoshi Sugawa, Tohoku University (Japan)
18:55ISS-093
0.8 um color pixels with wave-guiding structures for low optical crosstalk image sensors, Yu-Chi Chang, Cheng-Hsuan Lin, Zong-Ru Tu, Jing-Hua Lee, Sheng Chuan Cheng, Ching-Chiang Wu, Ken Wu, and H. J. Tsai, VisEra Technologies Company (Taiwan)
CONFERENCE INTERACTIVE POSTERS, DEMONSTRATIONS, AND BREAK
19:15 – 19:45
see below for location
Posters and/or Demonstrations presented live during this break are related to any of the conferences held today. Zoom links to visit the posters and/or demonstrations are found on the home page of the Symposium Portal. We invite you to visit with the presenters in the designated Zoom or meet with other attendees in Discord.
ISS-072
ZOOM A — ISS POSTER: Estimation of any fields of lens PSFs for image simulation, Sangmin Kim1, Daekwan Kim1, Kilwoo Chung1, and JoonSeo Yim2; 1Samsung Electronics Device Solutions and 2Samsung Electronics (Republic of Korea)
SD&A-100D
ZOOM B — SD&A DEMO: "Sourcing and qualifying passive polarised 3D TVs", Andrew Woods, Curtin University (Australia)
Andrew Woods will demonstrate how to source and qualify passive polarized 3D TVs.
Applications
Moderator:
Rihito Kuroda, Tohoku Univ. (Japan)
Session Chair:
Hans Reyserhove, Ceremorphic (United States)
19:45 – 20:45
Blue Room
19:45ISS-066
A single chip PPG sensor with enhanced IR sensitivity for low power and small size, Jungwook Lim1, Jihun Kim1, Long Yan1, Hyunpil Noh1, Junghyung Pyo1, Taesub Jung2, Jungbin Yun1, Seungki Jung1, Doosik Seol1, Kyungho Lee1, Takashi Nagano1, and JungChak Ahn1; 1Samsung Electronics Device Solutions and 2Samsung Electronics (Republic of Korea)
20:05ISS-067
Under display camera Quad Bayer raw image restoration using deep learning, Irina Kim, Yunseok Choi, Hayoung Ko, Dongpan Lim, Youngil Seo, Jeongguk Lee, Geunyoung Lee, Eundoo Heo, Seongwook Song, and SukHwan Lim, Samsung (Republic of Korea)
20:25ISS-068
Under display camera image recovery through diffraction compensation, Jeongguk Lee, Yunseok Choi, Han-Sol Lee, Eundoo Heo, Dongpan Lim, Geunyoung Lee, and Seongwook Song, Samsung Electronics (Republic of Korea)
Wednesday 20 January 2021
Imaging Systems I
Moderator:
Jon McElvain, Dolby Laboratories (United States)
Session Chair:
Peter Catrysse, Stanford University (United States)
10:00 – 11:15
Blue Room
10:00
Conference Introduction
10:15ISS-120
Programmable liquid crystal apertures and filters for photographic lenses, Henry Dietz, University of Kentucky (United States)
10:35ISS-121
DevCAM: An open-source multi-camera development system for embedded vision, Dominique Meyer, Meher Birlangi, and Falko Kuester, University of California, San Diego (United States)
10:55ISS-122
Validation of image systems simulation technology using a Cornell box, Zheng Lyu1, Krithin Kripakaran1, Max Furth2, Eric Tang3, Brian Wandell1, and Joyce Farrell1; 1Stanford University (United States), 2Brighton College (United Kingdom), and 3Henry M Gunn High School (United States)
11:15 – 11:45 SESSION BREAK: Join speakers in the EI2021 Discord Voice Channel corresponding to the color of the room in which the session occurs or join an Open Discord Channel of your choice. After a plenary, join the Plenary Discord Voice Channel.
11:15 – 11:45 Women-in-Engineering Speed Networking (Morning) - take a break from technical sessions to make new connections and greet old friends. Look for the ZOOM link in Discord #announcements.
Imaging Systems II
Moderator:
Jon McElvain, Dolby Laboratories (United States)
Session Chair:
Francisco Imai, Apple Inc. (United States)
11:45 – 12:45
Blue Room
11:45ISS-123
Creating, weaponizing, and detecting deep fakes (Invited), Hany Farid, University of California at Berkeley (United States)
Invited speaker Hany Farid is a professor at the University of California, Berkeley with joint appointments in electrical engineering, computer sciences, and the school of information. His research focuses on image analysis, digital forensics, and the intersection of technology and society particularly as it pertains to online harms. He received his undergraduate degree in computer science and applied mathematics from the University of Rochester (1989), his MS in computer science from SUNY Albany, and his PhD in computer science from the University of Pennsylvania (1997). Following a two-year post-doctoral fellowship in brain and cognitive sciences at MIT, he joined the faculty at Dartmouth College in 1999 where he remained until 2019. He is the recipient of an Alfred P. Sloan Fellowship, a John Simon Guggenheim Fellowship, and is a fellow of the National Academy of Inventors.
12:15ISS-124
Optical design and manufacturability of imaging lenses for high resolution sensors (Invited), Gregory Hollows, Edmund Optics (United States)
Invited speaker Gregory Hollows is the vice president of imaging at Edmund Optics, Inc., where he directs and manages Edmund’s Imaging Business Unit responsible for Edmund’s numerous lens offerings designed to service the demanding needs of industries such as machine vision, factory automation, life sciences, and autonomous vehicles. He is member of the Board of Directors for A3, The Association for Advancing Automation, and of the AIA, The Automated Imaging Association/Association for Advancing Imaging. At the AIA, he has served in numerous roles over the years, among them, chair of the board, education committee chair and tradeshow committee chair. A certified vision professional, Greg has taught numerous basic and advanced optics for the imaging industry. He is author of numerous technical articles and tutorials on optics and imaging and has degrees in physics and chemistry from Rutgers University.
KEYNOTE: Computational Capture
Moderator: Jon McElvain, Dolby Laboratories (United States)
Session Chair: Nitin Sampat, Edmund Optics, Inc (United States)
13:15 – 14:15
Blue Room
13:15ISS-128
KEYNOTE: Computational photography at the point of capture on mobile cameras, Marc Levoy, Adobe Inc. (United States)
Keynote speaker Marc Levoy is the VMware Founders Professor of Computer Science (Emeritus) at Stanford University, and a vice president and fellow at Adobe. From 2011 until 2020 he worked at Google, most recently as a distinguished engineer in Google Research. In previous lives he worked on computer-assisted cartoon animation (1970s), volume rendering (1980s), 3D scanning (1990s), light field imaging (2000s), and computational photography (2010s). At Stanford he taught computer graphics, digital photography, and the science of art. At Google he launched Street View, co-designed the library book scanner, and led the team that created HDR+, Portrait Mode, and Night Sight for Pixel smartphones. Awards include Cornell University Charles Goodwin Sands Medal for best undergraduate thesis (1976), National Science Foundation Presidential Young Investigator (1991), ACM SIGGRAPH Computer Graphics Achievement Award (1996), and ACM Fellow (2007). His Google team's software for Pixel phones won DP Review's Innovation of the Year (2017 and 2018) and Smartphone Camera of the Year (2019), Mobile World Congress's Disruptive Device Innovation Award (2019), and other awards.
13:55
Roundtable with Marc Levoy
14:15 – 18:00 Break in program to accommodate time zones.
Thursday 21 January 2021
PLENARY: The Development of Integral Color Image Sensors and Cameras
Session Chair: Jonathan B. Phillips, Google Inc. (United States)
10:00 – 11:10
Plenary Room
The development of integral color image sensors and cameras
Kenneth A. Parulski, Expert Consultant: Mobile Imaging (United States)
Kenneth Parulski is an expert consultant to mobile imaging companies and leads the development of ISO standards for digital photography. He joined Kodak in 1980 after graduating from MIT and retired in 2012 as research fellow and chief scientist in Kodak's digital photography division. His work has been recognized with a Technical Emmy and other major awards. Parulski is a SMPTE fellow and an inventor on more than 225 US patents.
11:10 – 11:40 SESSION BREAK: Join speakers in the EI2021 Discord Voice Channel corresponding to the color of the room in which the session occurs or join an Open Discord Channel of your choice. After a plenary, join the Plenary Discord Voice Channel.
14:30 – 18:00 Break in program to accommodate time zones.
Monday 25 January 2021
PLENARY: Making Invisible Visible
Session Chair: Jonathan B. Phillips, Google Inc. (United States)
10:00 – 11:10
Plenary Room
Making invisible visible
Ramesh Raskar, Associate Professor, MIT Media Lab (United States)
Ramesh Raskar is an associate professor at MIT Media Lab and directs the Camera Culture research group. His focus is on AI and imaging for health and sustainability. They span research in physical (e.g., sensors, health-tech), digital (e.g., automated and privacy-aware machine learning), and global (e.g., geomaps, autonomous mobility) domains. He received the Lemelson Award (2016), ACM SIGGRAPH Achievement Award (2017), DARPA Young Faculty Award (2009), Alfred P. Sloan Research Fellowship (2009), TR100 Award from MIT Technology Review (2004), and Global Indus Technovator Award (2003). He has worked on special research projects at Google [X] and Facebook and co-founded/advised several companies.
11:10 – 11:40 SESSION BREAK: Join speakers in the EI2021 Discord Voice Channel corresponding to the color of the room in which the session occurs or join an Open Discord Channel of your choice. After a plenary, join the Plenary Discord Voice Channel.
14:30 – 18:00 Break in program to accommodate time zones.
Wednesday 27 January 2021
PLENARY: Revealing the Invisible to Machines with Neuromorphic Vision Systems: Technology and Applications Overview
Session Chair: Radka Tezaur, Intel Corporation (United States)
10:00 – 11:10
Plenary Room
Revealing the invisible to machines with neuromorphic vision systems: Technology and applications overview
Luca Verre, CEO and Co-Founder at Prophesee (France)
Luca Verre is co-founder and CEO of Prophesee, the inventor of the world’s most advanced neuromorphic vision systems. Verre is a World Economic Forum technology pioneer. His experience includes project and product management, marketing, and business development roles at Schneider Electric. Prior to Schneider Electric, Verre worked as a research assistant in photonics at the Imperial College of London. Verre holds a MSc in physics, electronic and industrial engineering from Politecnico di Milano and Ecole Centrale and an MBA from Institut Européen d'Administration des Affaires, INSEAD.
11:10 – 11:40 SESSION BREAK: Join speakers in the EI2021 Discord Voice Channel corresponding to the color of the room in which the session occurs or join an Open Discord Channel of your choice. After a plenary, join the Plenary Discord Voice Channel.
13:00 – 13:30 SESSION BREAK: Join speakers in the EI2021 Discord Voice Channel corresponding to the color of the room in which the session occurs or join an Open Discord Channel of your choice. After a plenary, join the Plenary Discord Voice Channel.
14:30 – 18:00 Break in program to accommodate time zones.
19:15 – 19:45 SESSION BREAK: Join speakers in the EI2021 Discord Voice Channel corresponding to the color of the room in which the session occurs or join an Open Discord Channel of your choice. After a plenary, join the Plenary Discord Voice Channel.
19:15 – 19:45 Women-in-Engineering Speed Networking (Evening) - take a break from technical sessions to make new connections and greet old friends. Look for the ZOOM link in Discord #announcements.