Virtual Conference Program
Please go to the main conference page for live session streams and videos.
Technical papers will be presented with 12 minute pre-recorded presentation videos, followed by 3 minutes of live Q&A. Following the session, discussions between authors and attendees will continue asynchronously through comment/discussion threads. Poster and demo presentations will be available as pre-recorded 5 minute videos throughout the conference, with asynchronous discussions between authors and attendees through comment/discussion threads: attendees are encouraged to view and participate in discussions during the scheduled break between sessions. Keynote presentations and Q&A will be live.
Program Summary
All times in St. Louis timezone: CDT (UTC -0500)
| Friday, April 24th | |
|---|---|
| 10:30am-Noon | Welcome + Session 1.A (Live) #27, #61, #79, #86 |
| Noon-1:00pm | Virtual Discussion (Papers/Posters/Demos). |
| 1:00pm-2:00pm | Keynote: Ira Kemelmacher-Shlizerman |
| 2:00pm-3:00pm | Virtual Discussion (Papers/Posters/Demos). |
| 3:00pm-4:00pm | Session 1.B (Live) #2, #29, #55, #62 |
| 4:00pm-4:30pm | Virtual Discussion (Papers/Posters/Demos). |
| 4:30pm-5:30pm | Session 1.C (Live) #3, #22, #43, #54 |
| 5:30pm- | Virtual Discussion (Papers/Posters/Demos). |
| Saturday, April 25th | |
|---|---|
| 10:30am-11:30am | Session 2.A (Live) #11, #35, #37, #98 |
| 11:30am-12:30pm | Virtual Discussion (Papers/Posters/Demos). |
| 12:30pm-1:30pm | Keynote: Aude Oliva |
| 1:30pm-2:30pm | Virtual Discussion (Papers/Posters/Demos). |
| 2:30pm-3:30pm | Session 2.B (Live) #9, #16, #45, #69 |
| 3:30pm-4:30pm | Virtual Discussion (Papers/Posters/Demos). |
| 4:30pm-5:30pm | Session 2.C (Live) #21, #57, #91, #106 |
| 5:30pm- | Virtual Discussion (Papers/Posters/Demos). |
| Sunday, April 26th | |
|---|---|
| 10:30am-11:30am | Session 3.A (Live) #25, #81, #85, #93 |
| 11:30am-12:30pm | Virtual Discussion (Papers/Posters/Demos). |
| 12:30pm-1:30pm | Keynote: Mark Itzler |
| 1:30pm-2:30pm | Virtual Discussion (Papers/Posters/Demos). |
| 2:30pm-3:30pm | Session 3.B (Live) #1, #31, #50, #70 |
| 3:30pm-5:00pm | Virtual Discussion (Papers/Posters/Demos). |
| 5:00pm-5:30pm | Closing |
Detailed Program
Keynotes
Ira Kemelmacher-Shlizerman
Associate Professor, University of Washington. Director of UW Reality Lab. Fashion and AR Lead, Google.
Friday, 1:00 PM
Title: Getting Things Done
Abstract: I will talk about my team’s most recent research work in matting for video communication, 3D sports, and face synthesis.
Bio: Prof. Kemelmacher-Shlizerman is a Scientist and Entrepreneur. She is an Associate Professor of Computer Science at the Allen School University of Washington, where she is also the Director of the UW Reality Lab—a lab that is focused on research in AR/VR, computer vision, and computer graphics. Her Ph.D is in computer science and applied mathematics from the Weizmann Institute of Science. In parallel to Ira’s academic career, she founded the startup Dreambit, which was acquired by Facebook in 2016. She spent two years at Facebook building products. Before that, in 2011, Ira tech transferred the product Face Movies to Google. Currently Ira is also a Staff Research Scientist at Google where she leads a moonshot product. Her works were awarded the Google faculty award, Madrona prize, the GeekWire Innovation of the Year Award, 2016, selected to the covers of CACM and SIGGRAPH, and frequently covered by most national and international media.
Aude Oliva
Principal Research Scientist, MIT CSAIL. MIT Director MIT-IBM Watson AI Lab, co-director MIT Quest for Intelligence
Saturday, 12:30 PM
Title: Incorporating Insights from Cognitive Science into AI
Abstract: This talk will cover milestones in visual cognition and human neuroscience research which can inform the ongoing development of artificial intelligence systems. Building on cross-cutting advances in human and machine perception research, I will describe how we can design computational theories and models that are closer to how humans register visual scenes and events, focus their attention, and remember important visual information.
Bio: Aude Oliva is the MIT director of the MIT–IBM Watson AI Lab. She is also co-director of the MIT Quest for Intelligence and a principal research scientist at the Computer Science and Artificial Intelligence Laboratory. She formerly served as an expert to the National Science Foundation, Directorate of Computer and Information Science and Engineering. Her research interests span computer vision, cognitive science and human neuroscience. She has received an NSF Career Award, a Guggenheim Fellowship and a Vannevar Bush Faculty Fellowship. She earned a MS and PhD in cognitive science from the Institut National Polytechnique de Grenoble, France.
Mark Itzler
VP LiDAR, Argo AI.
Sunday, 12:30 PM
Title: Single-photon LiDAR Imaging: from airborne to automotive platforms
Abstract: Over the past decade, the benefits of single-photon sensitive Geiger-mode lidar have been established for high-altitude airborne applications, and this sensing technology is now poised for much broader deployment in 3D imaging systems for automotive platforms. A key innovation enabling these systems has been the development of shortwave infrared focal plane arrays with single-photon sensitivity and sub-nanosecond timing accuracy, and these sensors have also been employed in other high-precision time-of-flight applications such as long-range ground-based imaging and seeing around corners. In this talk, I will describe key attributes of this Geiger-mode sensor technology, its use in airborne lidar systems, and its current migration into autonomous vehicles. The unique combination of several factors—particularly single-photon sensitivity, the greater eye-safety of lasers at wavelengths beyond 1400 nm, and the use of arrayed semiconductor devices—provides a path toward realizing higher performance scalable lidar for automotive applications.
Bio: Mark Itzler is VP Lidar at Argo AI, where he provides technical leadership for the development of Argo’s high-performance long-range lidar product for autonomous vehicles. Mark came to Argo in 2017 through its acquisition of Princeton Lightwave Inc. (PLI), where he was Chief Executive Officer and Chief Technical Officer. Prior to joining PLI in 2003, Mark was the CTO and VP Device Engineering of the Epitaxx Division of JDSU. He received B.S. and Ph.D. degrees in Physics from Brown University and the University of Pennsylvania, respectively, and he pursued post-doctoral research at Harvard University. His technical focus has been semiconductor photodetector technology and its application to 3D lidar imaging, single-photon detection, and fiber optic communications. He has published over 100 papers, has 26 granted patents, and is an IEEE Fellow and SPIE Fellow.
Technical Paper Sessions
Session 1.A: Friday, 10:30 am - Noon
#27: NLDNet++: A Physics Based Single Image Dehazing Network. Iris Tal (Tel-Aviv University); Yael Bekerman (Tel Aviv University); Avi Mor (Motorola Solutions); Lior Knafo (Motorola Solutions); Jonathan Alon (Motorola Solutions); Shai Avidan (Tel Aviv University)
#61: Distributed Sky Imaging Radiometry and Tomography. Amit Aides (Google); Aviad Levis (Technion); Vadim Holodovsky (Technion); Yoav Y. Schechner (Technion); Dietrich Althausen (Leibniz Institute for Tropospheric Research); Adi Vainiger (Technion)
#79: Towards Learning-based Inverse Subsurface Scattering. Chengqian Che (Carnegie Mellon University); Fujun Luan (Cornell University); Shuang Zhao (University of California, Irvine); Kavita Bala (Cornell); Ioannis Gkioulekas (Carnegie Mellon University)
#86: Unveiling Optical Properties in Underwater Images. Yael Bekerman (Tel Aviv University); Shai Avidan (Tel Aviv University); Tali Treibitz (University of Haifa)
Session 1.B: Friday, 3:00 pm - 4:00 pm
#2: Raycast Calibration for Augmented Reality HMDs with Off-Axis Reflective Combiners. Qi Guo (Harvard University); Huixuan Tang (Facebook Reality Labs); Aaron Schmtiz (Facebook); Wenqi Zhang (Facebook Reality Labs); Yang Lou (Facebook Reality Lab); Alexander Fix (Facebook Reality Labs); Steven Lovegrove (Facebook Reality Labs); Hauke Malt (Facebook Reality Labs)
#29: Neural Opacity Point Cloud. Cen Wang (ShanghaiTech); Minye Wu (Shanghaitech University); Ziyu Wang (Shanghaitech University); Liao Wang (ShanghaiTech University); Hao Sheng (Beihang University); Jingyi Yu (Shanghai Tech University)
#55: Shape and Reflectance Reconstruction Using Concentric Multi-Spectral Light Field. Mingyuan Zhou (University of Delaware); Yuqi Ding (Louisiana State University); Yu Ji (Plex-VR); S. Susan Young (ARL); Jingyi Yu (Shanghai Tech University); Jinwei Ye (Louisiana State University)
#62: Multiscale-VR: Multiscale Gigapixel 3D Panoramic Videography for Virtual Reality. Jianing Zhang (Tsinghua University); Tianyi Zhu (Tsinghua University); Anke Zhang (Tsinghua University); Xiaoyun Yuan (HKUST); Zihan Wang (Tsinghua University); Sebastian Beetschen (Tsinghua); Lan Xu (HKUST); Xing Lin (Tsinghua University); Qionghai Dai (Tsinghua University); Lu Fang (Tsinghua University)
Session 1.C: Friday, 4:30 pm - 5:30 pm
#3: Programmable Spectrometry: Per-pixel Material Classification using Learned Spectral Filters. Vishwanath Saragadam (Carnegie Mellon University); Aswin C. Sankaranarayanan (Carnegie Mellon University)
#22: Learning a Probabilistic Strategy for Computational Imaging Sensor Selection. He Sun (California Institute of Technology); Adrian V. Dalca (MIT); Katherine L. Bouman (Caltech)
#43: Neural Sensors: Learning Pixel Exposures for HDR Imaging and Video Compressive Sensing with Programmable Sensors. Julien N. P. Martel (Stanford University); Lorenz K. Müller (IBM Research); Stephen J. Carey (The University of Manchester); Piotr Dudek (School of Electrical and Electronic Engineering, The University of Manchester, UK); Gordon Wetzstein (Stanford University)
#54: PhlatCam: Designed phase-mask based thin lensless camera. Vivek Boominathan (Rice University); Jesse K. Adams (Rice University); Jacob T. Robinson (Rice University); Ashok Veeraraghavan (Rice University)
Session 2.A: Saturday, 10:30 am - 11:30 am
#11: Deep Slow Motion Video Reconstruction with Hybrid Imaging System. Avinash Paliwal (Texas A&M University); Nima Khademi Kalantari (Texas A&M University)
#35: Per-Image Super-Resolution for Material BTFs. Dennis den Brok (University of Bonn); Sebastian Merzbach (University of Bonn); Michael Weinmann (University of Bonn); Reinhard Klein (University of Bonn)
#37: High Resolution Light Field Recovery with Fourier Disparity Layer Completion, Demosaicing, and Super-Resolution. Mikaël Le Pendu (Trinity College Dublin); Aljosa Smolic (Trinity College Dublin)
#98: One-Bit Time-Resolved Imaging. Ayush Bhandari (Imperial College London); Miguel Heredia Conde (University of Siegen); Otmar Loffeld (University of Siegen)
Session 2.B: Saturday, 2:30 pm - 3:30 pm
#9: SweepCam - Depth-aware Lensless Imaging using Programmable Masks. Yi Hua (Carnegie Mellon University); Shigeki Nakamura (Sony Semiconductor Solutions Corporation); M. Salman Asif (University of California, Riverside); Aswin C. Sankaranarayanan (Carnegie Mellon University)
#16: FoveaCam: A MEMS Mirror-Enabled Foveating Camera. Brevin Tilmon (University of Florida); Eakta Jain (University of Florida); Silvia Ferrari (Cornell); Sanjeev Koppal (University of Florida)
#45: Deep Adaptive LiDAR: End-to-end Optimization of Sampling and Depth Completion at Low Sampling Rates. Alexander W. Bergman (Stanford University); David B. Lindell (Stanford University); Gordon Wetzstein (Stanford University)
#69: End-to-End Video Compressive Sensing Using Anderson-Accelerated Unrolled Networks. Yuqi Li (King Abdullah University of Science and Technology); Miao Qi (King Abdullah University of Science and Technology); Rahul Gulve (University of Toronto); Mian Wei (University of Toronto); Roman Genov (University of Toronto); Kiriakos N. Kutulakos (University of Toronto); Wolfgang Heidrich (KAUST)
Session 2.C: Saturday, 4:30 pm - 5:30 pm
#21: Modeling Defocus-Disparity in Dual-Pixel Sensors. Abhijith Punnappurath (York University); Abdullah Abuolaim (York University); Mahmoud Afifi (York University); Michael S. Brown (York University)
#57: WISHED: Wavefront imaging sensor with high resolution and depth ranging. Yicheng Wu (Rice University); Fengqiang Li (Northwestern University); Florian Willomitzer (Northwestern University); Ashok Veeraraghavan (Rice University); Oliver Cossairt (Northwestern University)
#91: Distance Surface for Event-Based Optical Flow. Mohammed Almatrafi (Umm Al-Qura University ); Raymond Baldwin (University of Dayton); Kiyoharu Aizawa (The University of Tokyo); Keigo Hirakawa (University of Dayton)
#106: Fast confocal microscopy imaging based on deep learning. Xiu Li (Tsinghua University); Jiuyang Dong (Tsinghua University); Bowen Li (Tsinghua University); Yi Zhang (Tsinghua University); Yongbing Zhang (Tsinghua University); Ashok Veeraraghavan (Rice University); Xiangyang Ji (Tsinghua University)
Session 3.A: Sunday, 10:30 am - 11:30 am
#25: 3D Face Reconstruction using Color Photometric Stereo with Uncalibrated Near Point Lights. Zhang Chen (ShanghaiTech University); Yu Ji (Plex-VR); Mingyuan Zhou (University of Delaware); Sing Bing Kang (Zillow Group); Jingyi Yu (Shanghai Tech University)
#81: Comparing Vision-based to Sonar-based 3D Reconstruction. Netanel Frank (Tel Aviv University); Lior Wolf (Tel Aviv University, Israel); Danny Olshansky (Tel Aviv University); Arjan Boonman (Tel Aviv University); Yossi Yovel (Tel Aviv University)
#85: Action Recognition from a Single Coded Image. Tadashi Okawara (Osaka University); Michitaka Yoshida (Osaka University); Hajime Nagahara (Osaka University); Yasushi Yagi (Osaka University)
#93: Differential 3D Facial Recognition:Adding 3D to your State-of-the-Art 2D Method. J. Matias Di Martino (Universidad de la Republica); Fernando Suzacq (Universidad de la Republica); Mauricio Delbracio (Universidad de la Republica); Qiang Qiu (Duke University); Guillermo Sapiro (Duke University)
Session 3.B: Sunday, 2:30 pm - 3:30 pm
#1: The role of Wigner Distribution Function in Non-Line-of-Sight Imaging. Xiaochun Liu (University of Wisconsin - Madison); Andreas Velten (University of Wisconsin - Madison)
#31: High Resolution Diffuse Optical Tomography using Short Range Indirect Subsurface Imaging. Chao Liu (Carnegie Mellon University); Akash K. Maity (Rice University); Artur W. Dubrawski (CMU); Ashutosh Sabharwal (Rice University); Srinivasa G. Narasimhan (Carnegie Mellon University)
#50: Simulating Anisoplanatic Turbulence by Sampling Correlated Zernike Coefficients. Nicholas Chimitt (Purdue University); Stanley H. Chan (Purdue University, USA)
#70: Towards Reflectometry from Interreflections. Kfir Shem-Tov (Technion); Sai Praveen Bangaru (MIT); Anat Levin (Technion); Ioannis Gkioulekas (Carnegie Mellon University)
Posters & Demos
| #1 | Poster | Deep Outdoor Photometric Stereo | Yannick Hold-Geoffroy, Paulo Gotardo, Jean-François Lalonde |
| #2 | Poster | Real-time Seam Carving | Nicole Kosoris, Naila Fatima, Disha Das |
| #3 | Poster | 3D Scene Flow from 4D Light Field Gradients | Sizhuo Ma, Brandon M. Smith, Mohit Gupta |
| #4 | Poster | Multi-layer scattering model for incoherent fluorescence imaging with multiple-scattering phantom | Yi Xue, Laura Waller |
| #5 | Poster | Imaging through diffusers with extended depth-of-field using a deep neural network | Yunzhe Li, Shiyi Cheng, Yujia Xue, Lei Tian |
| #6 | Poster | Fourier-space Diffractive Deep Neural Network | Tao Yan, Jiamin Wu, Tiankuang Zhou, Hao Xie, Feng Xu, Jingtao Fan, Lu Fang, Xing Lin, Qionghai Dai |
| #7 | Poster | Phasor field diffraction based reconstruction for fast non-line-of-sight imaging systems | Xiaochun Liu, Ji Hyun Nam, Sebastian Bauer, Andreas Velten |
| #8 | Poster | Dynamic Fluid Surface Reconstruction Using Deep Neural Network | Simron Thapa, Nianyi Li, Jinwei Ye |
| #9 | Poster | On-chip fluorescence microscopy with a random microlens diffuser | Grace Kuo, Fanglin (Linda) Liu, Kristina Monakhova, Kyrollos Yanny, Ren Ng, Laura Waller |
| #10 | Poster | Joint optimization for compressive color video sensing and reconstruction under hardware constraints | Michitaka Yoshida, Akihiko Torii, Masatoshi Okutomi, Kenta Endo, Yukinobu Sugiyama, Rin-ichiro Taniguchi, Hajime Nagahara |
| #11 | Poster | Joint Filtering of Intensity Images and Neuromorphic Events for High-Resolution Noise-Robust Imaging | Zihao W. Wang, Peiqi Duan, Oliver Cossairt, Aggelos Katsaggelos, Tiejun Huang, Boxin Shi |
| #12 | Poster | A Coding Theory of Time-of-Flight Imaging | Felipe Gutierrez-Barragan, Andreas Velten, Mohit Gupta |
| #13 | Poster | Using Corners to See Around Corners with Edge-Resolved Transient Imaging | Joshua Rapp, Charles Saunders, Julian Tachella, John Murray-Bruce, Yoann Altmann, Jean-Yves Tourneret, Stephen McLaughlin, Robin M. A. Dawson, Franco N. C. Wong, Vivek K Goyal |
| #14 | Poster | Deep Compressed Sensing for HDR Image Acquisition | Neerja Thakkar, Julio Marco, Adrian Jarabo, Diego Gutierrez, Ana Serrano |
| #16 | Poster | Photosequencing of Motion Blur using Short and Long Exposures | Vijay Rengarajan, Shuo Zhao, Ruiwen Zhen, John Glotzbach, Hamid Sheikh, Aswin C. Sankaranarayanan |
| #17 | Poster | HeartCam: Camera-based physiology monitoring in-the-wild | Ewa Magdalena Nowara, Tim K. Marks, Hassan Mansour, Daniel McDuff, Ashok Veeraraghavan |
| #18 | Poster | Design and Calibration of a Fast Flying-Dot Projector for Dynamic Light Transport Acquisition | Kristofer Henderson, Xiaomeng Liu, Justin Folden, Brevin Tilmon, Suren Jayasuriya, Member, Sanjeev Koppal |
| #19 | Poster | Glitter as a Single Image Camera Calibration Object | Maya Shende, Abby Stylianou, Robert Pless |
| #20 | Poster | Super-Resolution Light-in-Flight Imaging using SPAD-CCD Sensor Fusion | Clara Callenberg, Ashley Lyons, Dennis den Brok, Daniele Faccio, Matthias Hullin |
| #21 | Poster | Learned Large Field-of-View Imaging with Thin-Plate Optics | Yifan (Evan) Peng, Qilin Sun, Xiong Dun, Gordon Wetzstein, Wolfgang Heidrich, Felix Heide |
| #22 | Poster | Direct Sparse-View CT Reconstruction using LSTM Processing of Stacked Back Projections | Wenrui Li, Gregery T. Buzzard, Charles A. Bouman |
| #23 | Poster | Single-shot Monocular RGB-D Imaging using Uneven Double Refraction | Andreas Meuleman, Seung-Hwan Baek, Felix Heide, Min H. Kim |
| #24 | Poster | Optimal HDR and Depth from Dual Cameras | Pradyumna Chari, Anil Kumar Vadathya, Kaushik Mitra |
| #25 | Poster | Computational Sensor Fingerprints | Pawel Korus, Eric Wengrowski, Nasir Memon |
| #26 | Poster | Single-Photon 3D Cameras | Atul Ingle, Anant Gupta, Andreas Velten, Mohit Gupta |
| #27 | Poster | Passive High Dynamic Range Imaging with Single-Photon Sensors | Trevor Seets, Atul Ingle, Andreas Velten, Mohit Gupta |
| #28 | Poster | Source Shot Noise Mitigation in Focused Ion Beam Microscopy by Time-Resolved Measurement | Minxu Peng, John Murray-Bruce, Karl K. Berggren, Vivek K. Goyal |
| #29 | Poster | 2D Corner Camera: Occluder-aided estimation of non-line-of-sight scenes from a single photograph | Sheila W. Seidel, John Murray-Bruce, Yanting Ma, Christopher Yu, William T. Freeman, Vivek K. Goyal |
| #30 | Poster | Surface Normal Estimation from Pulse Broadening in Single-Photon Lidar | Zhijian Li, Joshua Rapp, Vivek K Goyal |
| #31 | Poster | Probing Coherent Transmission and Incoherent Transport with Coded Coherence Interferometry | Alankar Kotwal, Anat Levin, Ioannis Gkioulekas |
| #33 | Poster | Visual Physics: Discovering Physical Laws from Videos | Pradyumna Chari, Chinmay Talegaonkar, Yunhao Ba, Achuta Kadambi |
| #34 | Poster | Single-shot 3D Microscopy | Fanglin Linda Liu, Grace Kuo, Nick Antipa, Laura Waller |
| #36 | Poster | Learning Rank-1 Diffractive Optics for Single-shot High Dynamic Range Imaging | Qilin Sun, Ethan Tseng, Qiang Fu, Wolfgang Heidrich, Felix Heide |
| #37 | Poster | Image Manipulation Detection Based on Planckian Locus | Setareh Kian, Scott McCloskey, Keigo Hirakawa |
| #39 | Poster | A hardware based approach for adaptive LiDAR | Francesco Pittaluga, Zaid Tasneem, Justin Folden, Brevin Tilmon, Ayan Chakrabarti, Sanjeev Koppal |
| #40 | Poster | Differentiable Programming for Hyperspectral Unmixing using a Physics-based Dispersion Model | John Janiczek, Parth Kashyap Thaker, Gautam Dasarathy, Christopher Scott Edwards, Phil Christensen, Suren Jayasuriya |
| #41 | Poster | Physics-based Machine Learning for Synthetic Aperture Sonar | Albert Reed, Suren Jayasuriya |
| #42 | Poster | Towards Robust Lensless Image Reconstruction via PSF Estimation | Joshua Rego, Suren Jayasuriya |
| #43 | Poster | Deep Polarization Cues for Transparent Object Segmentation | Agastya Kalra, Vage Taamazyan, Supreeth Krishna Rao, Kartik Venkataraman, Ramesh Raskar, Achuta Kadambi |
| #44 | Demo | FoveaCam: A MEMS Mirror-Enabled Foveating Camera | Brevin Tilmon, Eakta Jain, Silvia Ferrari, Sanjeev Koppal |
| #45 | Demo | Compact single-shot metalens depth sensor inspired by eyes of jumping spiders | Qi Guo, Zhujun Shi, Yao-Wei Huang, Emma Alexander, Cheng-Wei Qiu, Federico Capasso, Todd Zickler |
| #47 | Demo | Programmable Light Curtain | Joe Bartels, Srinivas Narasimhan |