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.
14:30 – 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.
System Performance I
Moderator:
Sophie Triantaphillidou, University of Westminster (United Kingdom)
Session Chairs:
Peter Burns, Burns Digital Imaging (United States) and Mylène Farias, University of Brasilia (Brazil)
11:40 – 13:00
Blue Room
11:40IQSP-215
Evaluation of the lens flare, Elodie Souksava1,2, Thomas Corbier1, Alexandra Giraud1,3, François-Xavier Thomas1, Laurent Chanas1, and Frédéric Guichard1; 1DxOMark Image Labs, 2Sorbonne Universite, and 3Institut d'Optique Graduate School (France)
12:00IQSP-216
Corner cases and limitations using a DOE based geometric camera calibration, Dietmar Wueller, Image Engineering GmbH & Co. KG (Germany)
12:20IQSP-217
Using images of noise to visualize image processing behavior, Norman Koren, Imatest LLC (United States)
12:40IQSP-218
RAW image quality evaluation using information capacity, François-Xavier Thomas, Thomas Corbier, Emilie Baudin, Yiqi Li, Laurent Chanas, and Frédéric Guichard, DxOMark Image Labs (France)
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.
IQSP-196
ZOOM A — IQSP POSTER: Understanding the importance of artistic aspect of camera image quality tuning and quantifying the artistic attributes by using scientific principles, Vickrant Zunjarrao, Ranga Burada, Sharvin Shobhane, and Lekha Lokhande, Microsoft Corporation (United States)
Industry Perspectives on Mobile Image Quality I
Moderator:
Susan Farnand, Rochester Institute of Technology (United States)
Session Chairs:
Elaine Jin, Intuitive Surgical (United States) and Sophie Triantaphillidou, University of Westminster (United Kingdom)
13:30 – 14:30
Blue Room
13:30IQSP-203
From the beginning until now - Twenty years of subjective mobile phone camera photography and image quality development (Invited), Tero Vuori, Xiaomi (Finland)
Invited speaker Tero Vuori is senior manager, camera and image quality at Xiaomi Technology, Tampere, Finland. Vuori is a camera and imaging professional with 20 years' experience in imaging and camera engineer and manager positions in companies like Nokia, Microsoft, Intel, and Xiaomi. He is a successful contributor as IQ tech lead, team lead, IQ architect, engineering manager, camera engineer, scrum master, and product owner. His background includes IQ testing architectures for R&D milestones in camera and imaging systems (sensors, optics, camera modules, ISP pipes, 3A, algorithms, and camera IQ tunings) and multiple IQ testing standards and test procedures widely used in the digital camera industry.
13:50IQSP-204
VCX Version 2020 – Further development of a transparent and objective evaluation scheme for mobile phone cameras, Uwe Artmann, Image Engineering GmbH & Co KG (Germany)
14:10IQSP-205
The gaps between development and research in mobile image processing (Invited), Artem Zinevich, Amazon Lab126 (United States)
Invited speaker Artem Zinevich, PhD, is a principal engineer - video quality with Amazon Lab126 in Sunnyvale, CA. Zinevich is currently specializing in digital imaging, and has contributed in a variety of domains - market-leading digital image processors, speech recognition, first of its kind monitoring of atmosphere via cellular networks, and seismic signal processing. His specialties include imaging systems, image signal processors (ISPs) - architecture & algorithms, still and video cameras, image sensors; machine learning and speech recognition, software (C/C++, Matlab, Python, Perl, embedded, scripting, etc.); and team building and leadership, project and program management, critical chain and agile, product ownership, and customer relations.
14:30 – 18:00 Break in program to accommodate time zones.
Industry Perspectives on Mobile Image Quality II
Moderator:
Stuart Perry, University of Technology Sydney (Australia)
Session Chairs:
Brian Cooper, Lexmark (United States) and Elaine Jin, Intuitive Surgical (United States)
18:00 – 19:15
Blue Room
18:00
Conference Introduction
18:15IQSP-206
Camera image quality tradeoff processing of image sensor re-mosaic using deep neural network, Younghoon Kim, Jungmin Lee, Sung-su Kim, Jiyun Bang, Dagyum Hong, TaeHyung Kim, and JoonSeo Yim, Samsung Electronics (Republic of Korea)
18:35IQSP-207
MIPI camera solution: Opportunity and challenges for Chromebook camera (Invited), Fei Wu, Google Inc. (United States)
Invited speaker Fei Wu is an engineer at Google, Inc., working in the areas of machine learning, deep learning, computer vision, and neuro-linguistic programming (NLP).
18:55
IQSP Discussion
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.
IQSP-197
ZOOM A — IQSP POSTER: Automatic image quality tuning framework for optimization of ISP parameters based on multi-stage optimization approach, Pavithra G and Radhesh Bhat, PathPartner Technology Pvt Ltd (India)
IQSP-198
ZOOM B — IQSP POSTER: Quantitative image quality evaluation method for UDC (under display camera), Sungho Cha, Samsung Electronics (Republic of Korea)
System Performance II
Moderator:
Luke Cui, Amazon (United States)
Session Chairs:
Susan Farnand, Rochester Institute of Technology (United States) and Stuart Perry, University of Technology Sydney (Australia)
19:45 – 20:25
Blue Room
19:45IQSP-219
Experimental study for revising visual noise measurement of ISO 15739, Akira Matsui1, Naoya Katoh1, and Dietmar Wueller2; 1Sony Imaging Products & Solutions Inc. (Japan) and 2Image Engineering GmbH & Co. KG (Germany)
20:05IQSP-220
A new PDAF correction method of CMOS image sensor with Nonacell and Super-PD to improve image quality in binning mode, Yeongheup Jang, Sansung Electronics (Republic of Korea)
Tuesday 26 January 2021
Visual Quality Metrics I
Moderator:
Jukka Häkkinen, University of Helsinki (Finland)
Session Chairs:
Mohamed Chaker Larabi, Université de Poitiers (France) and Sophie Triantaphillidou, University of Westminster (United Kingdom)
10:00 – 11:15
Green Room
10:00
Conference Introduction
10:15IQSP-261
Analyzing the effect of adding temporal features to an autoencoder-based video quality model, André Costa1, Helard Martinez2, Daniel Silva1, and Mylène Farias1; 1Universidade de Brasilia (Brazil) and 2University College Dublin (Ireland)
10:35IQSP-262
A comprehensive analysis of crowdsourcing for subjective evaluation of tone mapping operators, Ali Ak1, Abhishek Goswami2,3, Wolf Hauser3, Patrick Le Callet1, and Frederic Dufaux2; 1Universite de Nantes, 2Centre National de la Recherche Scientifique, and 3DxO Labs (France)
10:55IQSP-263
Quality is in the salient region of the image, Meisam Jamshidi Seikavandi1 and Seyed Ali Amirshahi2; 1Lorestan Technology and Science Park (Iran) and 2Norwegian University of Science and Technology (Norway)
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.
Visual Quality Metrics II
Moderator:
Peter Burns, Burns Digital Imaging (United States)
Session Chairs:
Nicolas Bonnier, Apple Inc. (United States) and Sophie Triantaphillidou, University of Westminster (United Kingdom)
11:45 – 12:45
Green Room
11:45IQSP-264
Enhancement of pixel-based video quality models using metadata, Rakesh Rao Ramachandra Rao, Steve Göring, and Alexander Raake, Technische University Ilmenau (Germany)
12:05IQSP-265
No-reference image quality assessment of underwater images using multi-scale salient local binary patterns, Muhammad Irshad1, Camilo Sanchez Ferreira2, Sana Alamgeer1, Carlos H. Llanos1, and Mylène Farias1; 1University of Brasilia (Brazil) and 2Universidad del Cauca (Colombia)
12:25IQSP-266
Exploring the boundaries of an AE-based quality model: A performance analysis via synthetic content, Helard Becerra1, Bruna Azambuja2, André Costa2, Andrew Hines1, and Mylène Farias2; 1University College Dublin (Ireland) and 2Universidade de Brasilia (Brazil)
CONFERENCE INTERACTIVE POSTERS, DEMONSTRATIONS, AND BREAK
12:45 – 13:15
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.
IPAS-226
ZOOM A — IPAS POSTER: Projection methods for finding intersection of two convex sets and their use in signal processing problems, Zuzana Bilkova1,2; 1Institute of Information Theory and Automation and 2Charles University in Prague (Czechia)
IQSP-224
ZOOM B — IQSP POSTER: Neural network-based assessment of the impact induced in video quality assessment by the semantic labels, Celestin Hernandez, Zacharie De La Lande Dolce, Rania Bensaied, and Mihai Mitrea, Institut Mines-Telecom (France)
IQSP-225
ZOOM C — IQSP POSTER: Saliency-based deep blind image quality assessment, Kamal Lamichhane1, Marco Carli1, and Federica Battisti2; 1Università degli Studi Roma TRE and 2University of Padova (Italy)
Quality of Immersive Applications I
Moderator:
Mohamed Chaker Larabi, Université de Poitiers (France)
Session Chairs:
Peter Burns, Burns Digital Imaging (United States) and Mylène Farias, University of Brasilia (Brazil)
13:15 – 14:15
Green Room
13:15IQSP-255
A content-based viewport prediction model, Dario Morais1, Lucas Althoff1, Ravi Prakash2, Marcelo Carvalho1, and Mylène Farias1; 1Universidade de Brasilia (Brazil) and 2The University of Texas at Dallas (United States)
13:35IQSP-256
A novel point cloud quality assessment metric based on perceptual color distance patterns, Rafael Diniz, Mylène Farias, and Pedro Garcia Freitas, Universidade de Brasilia (Brazil)
13:55IQSP-257
A deep perceptual metric for 3D point clouds, Maurice Quach1, Aladine Chetouani1,2, Giuseppe Valenzise1, and Frederic Dufaux1; 1Universite Paris-Saclay and 2University of Orléans (France)
14:15 – 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.
Quality of Immersive Applications II
Moderator:
Mylène Farias, University of Brasilia (Brazil)
Session Chairs:
Susan Farnand, Rochester Institute of Technology (United States) and Mohamed Chaker Larabi, Université de Poitiers (France)
11:40 – 13:00
Red Room
11:40IQSP-294
Effectiveness of VR immersive applications for public speaking enhancement, Arianna Notaro, Fabio Capraro, Marco Pesavento, Simone Milani, and Maria Grazia Busà, Universita degli Studi di Padova (Italy)
12:00IQSP-295
Quality assessment of super-resolved omnidirectional image quality using tangential views, Cagri Ozcinar1 and Aakanksha Rana2; 1Samsung Research UK (United Kingdom) and 2Massachusetts Institute of Technology (United States)
12:20IQSP-296
On the influence of head-mounted displays on visual quality rating, Aberrezzaq Sendjasni and Mohamed Chaker Larabi, Université de Poitiers (France)
12:40IQSP-297
No-reference stereoscopic image quality predictor using deep features from cyclopean image, Oussama Messai1, Aladine Chetouani2, Fella Hachouf1, and Zianou Ahmed Seghir3; 1University of Mentouri Brothers Constantine 1 (Algeria), 2University of Orléans (France), and 3University of Abbes Laghrour (Algeria)
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.
KEYNOTE: Quality of Immersive Applications
Session Chairs: Peter Burns, Burns Digital Imaging (United States) and Mylène Farias, University of Brasilia (Brazil)
Moderator: Mohamed Chaker Larabi, Université de Poitiers (France)
13:30 – 14:30
Red Room
IQSP-278
KEYNOTE: Quality of visual immersion: The point clouds perspective, Fernando Pereira, Instituto Superior Técnico - Instituto de Telecomunicações (Portugal)
Keynote speaker Fernando Pereira is currently a professor at Instituto Superior Técnico, Universidade de Lisboa, and a senior researcher at Instituto de Telecomunicações, Lisbon, Portugal. He was an IEEE Distinguished Lecturer in 2005 and was elected as an IEEE Fellow in 2008 for “contributions to object-based digital video representation technologies and standards”. He was elected to serve on the Signal Processing Society Board of Governors in the capacity of Member-at-Large for a 2012 and a 2014-2016 term. Since January 2018, he is the SPS vice-president for conferences. Since 2013, he is also a EURASIP Fellow for “contributions to digital video representation technologies and standards”. He was elected to serve on the European Signal Processing Society Board of Directors for a 2015-2018 term. Since 2015, he is also a IET Fellow. He was the MPEG Requirements Chair from 2002 to 2007 and has been the JPEG Requirements Chair since February 2016. He was the general chair of the Picture Coding Symposium (PCS) in 2007, the technical program co-chair of the Int. Conference on Image Processing (ICIP) in 2010 and 2016, the technical program chair of the International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS) in 2008 and 2012, and the general chair of the International Conference on Quality of Multimedia Experience (QoMEX) in 2016. He has contributed more than 300 papers in international journals, conferences, and workshops, and made numerous invited talks at conferences and workshops. His areas of interest are visual data analysis, coding, description, adaptation, and quality assessment, in the context of advanced multimedia services.
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.