IEEE SPS Computational Imaging Webinar Series

Signal Processing And Computational imagE formation (SPACE)

About SPACE Webinar Series

Given the impossibility of travel during the COVID-19 crisis, IEEE Computational Imaging TC is launching an SPS Webinar Series SPACE (Signal Processing And Computational imagE formation) as a regular bi-weekly online seminar series to reach out to the global computational imaging and signal processing community.

We have successfully completed our Season 1 from May to Dec 2020. We are now starting our Season 2 in 2021! Stay tuned.

The seminar series will use the Zoom Webinar platform, and at each seminar one keynote speaker will give a lecture, which is followed by Q&A and discussions.

Speakers for 2020 Season 1

  1. Raja Giryes (Tel Aviv University)

  2. Laura Waller (UC Berkeley)

  3. Michael Unser (EPFL)

  4. Katie Bouman (Caltech)

  5. Jong Chul Ye - (KAIST)

  6. Orazio Gallo (NVIDIA)

  7. Xiao Xiang Zhu (TUM)

  8. Saiprasad Ravishankar (Michigan State University)

  9. Anat Levin (Technion)

  10. Pier Luigi Dragotti (Imperial College)

  11. John Wright (Columbia University)

  12. Bihan Wen (NTU)

  13. Nicole Seiberlich (UMich)

  14. Yoram Bresler (UIUC)

  15. Singanallur V Venkatakrishnan (Oak Ridge National Laboratory)

  16. J. Webster Stayman (Johns Hopkins)

All talks are scheduled at 10:00am New York Time ( UTC -4 ), 3:00pm London Time ( UTC +1 ), 11:00pm Beijing Time ( UTC +8 ) , every other Tuesday. For attendees from other time zones, please use the [ time zone converter ]. Talks will be approximately 1 hour, followed by Q&A and discussions.

  • Check out more about SPACE invited speakers here: [ Invited Speakers ].

  • Check out the detailed SPACE program here: [ Program ]

How to Attend

We will use Zoom Webinars and YouTube to deliver the lectures.

Attendees can register via [ link ] to obtain the Zoom link with password. Since the Zoom Webinar can only host up to 500 attendees, additional attendees will be directed to our YouTube channel to watch the streaming.

Upcoming Talk

New Season 2021 starts!

June 23, 2021, Sabine Süsstrunk, ( EPFL )

    • Title: Opponency Revisted

    • Abstract: According to the efficient coding hypothesis, the goal of the visual system should be to encode the information presented to the retina with as little redundancy as possible. From a signal processing point of view, the first step in removing redundancy is de-correlation, which removes the second order dependencies in the signal. This principle was explored in the context of trichromatic vision by Buchsbaum and Gottschalk (1) and later Ruderman et al. (2) who found that linear de-correlation of the LMS cone responses matches the opponent color coding in the human visual system. In this talk, I will illustrate with several examples from our research that considering opponent colors can significantly improve image processing and computer vision tasks. We have in addition extended the concept of “color opponency” to include near-infrared. And we found that the de-correlation concept also applies to deep learning models in rather interesting ways.

Season 2 (2021)

  1. Feb 9, 2021, YongKeun Park, Quantitative phase imaging and artificial intelligence: label-free 3D imaging, classification, and inference.

  1. Feb 23, 2021, Pier Luigi Dragotti, Computational Imaging for Art Investigation: Revealing Hidden Drawings in Leonardo’s Paintings

  2. Mar 9, 2021, Gordon Wetzstein, Towards Neural Signal Processing and Imaging

  3. Mar 24, 2021, Yonina Eldar, Model Based Deep Learning: Applications to Imaging and Communications

  4. Apr 6, 2021, Ivan Dokmanić, Learning the Geometry of Wave-Based Imaging

  5. Apr 20, 2021, Ori Katz, Imaging with scattered light: Exploiting speckle to see deeper and sharper

  6. May 4, 2021, Lei Tian, Model and learning strategies for computational 3D phase microscopy

  7. May 18, 2021, Rebecca Willet , Machine Learning and Inverse Problems in Imaging

  8. June 1, 2021, Marvin M. Doyley, Elastography from theory to practice

Season 1 (May - Dec, 2020)

  1. May 19, 2020, Raja Giryes, Joint Design of Optics and Post-Processing Algorithms Based on Deep Learning for Generating Advanced Imaging Features.

  1. June 2, 2020, Laura Waller, End-To-End Learning for Computational Microscopy

  2. June 16, 2020, Michael Unser, CryoGAN: A novel paradigm for single-particle analysis and 3D reconstruction in cryo-EM microscopy

  3. June 30, 2020, Katie Bouman, Capturing the First Image of a Black Hole & Designing the Future of Black Hole Imaging

  4. July 14, 2020, Jong Chul Ye , Optimal transport driven CycleGAN for unsupervised learning in inverse problems

  5. July 28, 2020, Orazio Gallo , Depth Estimation from RGB Images with Applications to Novel View Synthesis and Autonomous Navigation

  6. August 11, 2020, Xiao Xiang Zhu, Data Science in Earth Observation

  7. August 25, 2020, Saiprasad Ravishankar, From Transform Learning to Deep Learning and Beyond for Imaging

  8. Sep 8, 2020, Anat Levin , Rendering speckle statistics in scattering media and its applications in computational imaging

  9. Oct 6, 2020, John Wright , Geometry and Symmetry in (some!) Nonconvex Optimization Problems

  10. Oct 20, 2020, Bihan Wen , From Signal Processing to Machine Learning: How "Old" Ways Can Join The New

  11. Nov 3, 2020, Nicole Seiberlich , Bringing New Imaging Technologies to the Clinic

  12. Nov 17, 2020, Yoram Bresler , Two Topics in Deep Learning for Image Reconstruction: (i) Physics-based x-ray scatter correction for CT; and (ii) Adversarial training for improved robustness.

  13. Dec 1, 2020, Singanallur V Venkatakrishnan, Pushing the Limits of Scientific CT Instruments using Algorithms : Model-based and Data-Driven Approaches

18. Dec 15, 2020, J. Webster Stayman, Novel data acquisition and task-based optimization in computed tomography


[ Webinar Organizing Committee ]