BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Europe/Paris BEGIN:DAYLIGHT DTSTART:20260329T030000 TZOFFSETFROM:+0100 TZOFFSETTO:+0200 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3 TZNAME:CEST END:DAYLIGHT BEGIN:STANDARD DTSTART:20261025T020000 TZOFFSETFROM:+0200 TZOFFSETTO:+0100 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10 TZNAME:CET END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20261017T195829Z UID:9D4DD00A-DBF7-4F53-B3D8-4D01BFDAC1B8 DTSTART;TZID=Europe/Paris:20261014T140000 DTEND;TZID=Europe/Paris:20261014T150000 DESCRIPTION:Title: Physics-Driven AI for Computational Imaging: Reconstruct ion\, Analysis and Generation\n\nAbstract:\n\nModern computational imaging systems capture rich visual information across diverse modalities and sca les\, yet translating raw measurements into accurate\, interpretable repre sentations remains a fundamental challenge. This talk presents our recent advances in physics-driven machine learning for computational imaging\, sp anning three interconnected themes: reconstruction\, analysis\, and genera tion. In the reconstruction thread\, we explore novel view synthesis\, 3D scene understanding\, and high-fidelity sparse-view reconstruction. In the analysis thread\, we discuss how to leverage physical prior and how found ation models can be grounded with physical constraints for robust generali sation. In the generation thread\, we present physics-aware approaches for reflection removal and shadow removal that disentangle physically distinc t image formation components. Across all themes\, a unifying philosophy em erges: embedding domain knowledge of underlying optical physics into the l earning framework yields models that are more accurate\, data-efficient\, and interpretable.\n\nBio:\n\nDr. Bihan Wen is currently an Associate Prof essor\, Provost's Chair in Artificial Intelligence for Computational Imagi ng\, Director of the CISS-ROSE Research Centre at Nanyang Technological Un iversity\, Singapore. He received the MS and PhD degrees in Electrical and Computer Engineering from the University of Illinois at Urbana-Champaign (UIUC)\, USA\, in 2015 and 2018\, respectively. His research interests inc lude artificial intelligence\, computational imaging\, image and video pro cessing. Dr. Wen is an IEEE Senior Member. He currently serves as a member of the IEEE Visual Signal Processing and Communications TC (2022-present) and IEEE Image\, Video\, and Multidimensional Signal Processing TC (2026- present)\, and as Vice Chair of the IEEE Signal Processing Society Singapo re Chapter. He is currently an Associate Editor for IEEE Signal Processing Magazine (2026-Present)\, Guest Editor for IEEE TMM and Pattern Recogniti on. He was a member (2018-2021) and SubCommittee Chair (2021-2024) of the IEEE Computational Imaging TC\, served as Associate Editor for IEEE T-CSVT (2020-2026)\, and as Conference Program Chair for IEEE MIPR 2022\, IEEE I CARCV 2024\, IEEE VCIP 2026\, and IEEE ICARCV 2026. He regularly serves as Area Chair for IEEE ICIP\, ICASSP\, ICME\, ISCAS\, and AAAI. Dr. Wen rece ived the 2026 Graduate Student Mentoring Award\, 2025 Research Young Facul ty Award (Runner-Up)\, and 2022 Early-Career Teaching Excellence Award fro m NTU. He received the 2026 Advanced Imaging Early Career Award from CIOP\ , and 2023 IEEE VSPC Rising Star (Runner-Up) from IEEE VSCP. He received t he Best Paper Awards at IEEE ICIEA 2023 and IEEE MIPR 2023\, and Best Pape r Award (Runner-Up) from IEEE ICME 2020. He has been ranked among the Worl d Top 2% Scientists in Artificial Intelligence by Stanford University and the Top 0.05% Highly Cited Scholar by ScholarGPS.\n\nVirtual: https://even ts.vtools.ieee.org/m/582761 LOCATION:Virtual: https://events.vtools.ieee.org/m/582761 ORGANIZER:Ambarish.natu@gmail.com SEQUENCE:6 SUMMARY:Physics-Driven AI for Computational Imaging: Reconstruction\, Analy sis and Generation URL;VALUE=URI:https://events.vtools.ieee.org/m/582761 X-ALT-DESC:Description: <br /><p><strong>Title:&nbsp\;Physics-Driven AI for Computational Imaging: Reconstruction\, Analysis and Generation<br></stro ng><br><strong>Abstract:</strong></p>\n<div>&nbsp\;</div>\n<div>Modern com putational imaging systems capture rich visual information across diverse modalities and scales\, yet translating raw measurements into accurate\, i nterpretable representations remains a fundamental challenge. This talk pr esents our recent advances in physics-driven machine learning for computat ional imaging\, spanning three interconnected themes: reconstruction\, ana lysis\, and generation. In the reconstruction thread\, we explore novel vi ew synthesis\, 3D scene understanding\, and high-fidelity sparse-view reco nstruction. In the analysis thread\, we discuss how to leverage physical p rior and how foundation models can be grounded with physical constraints f or robust generalisation. In the generation thread\, we present physics-aw are approaches for reflection removal and shadow removal that disentangle physically distinct image formation components. Across all themes\, a unif ying philosophy emerges: embedding domain knowledge of underlying optical physics into the learning framework yields models that are more accurate\, data-efficient\, and interpretable.<br><br></div>\n<div>&nbsp\;</div>\n<d iv><strong>Bio:</strong></div>\n<div>&nbsp\;</div>\n<div>Dr. Bihan Wen is currently an Associate Professor\, Provost's Chair in Artificial Intellige nce for Computational Imaging\, Director of the CISS-ROSE Research Centre at Nanyang Technological University\, Singapore. He received the MS and Ph D degrees in Electrical and Computer Engineering from the University of Il linois at Urbana-Champaign (UIUC)\, USA\, in 2015 and 2018\, respectively. His research interests include artificial intelligence\, computational im aging\, image and video processing. Dr. Wen is an IEEE Senior Member. He c urrently serves as a member of the IEEE Visual Signal Processing and Commu nications TC (2022-present) and IEEE Image\, Video\, and Multidimensional Signal Processing TC (2026-present)\, and as Vice Chair of the IEEE Signal Processing Society Singapore Chapter. He is currently an Associate Editor for IEEE Signal Processing Magazine (2026-Present)\, Guest Editor for IEE E TMM and Pattern Recognition. He was a member (2018-2021) and SubCommitte e Chair (2021-2024) of the IEEE Computational Imaging TC\, served as Assoc iate Editor for IEEE T-CSVT (2020-2026)\, and as Conference Program Chair for IEEE MIPR 2022\, IEEE ICARCV 2024\, IEEE VCIP 2026\, and IEEE ICARCV 2 026. He regularly serves as Area Chair for IEEE ICIP\, ICASSP\, ICME\, ISC AS\, and AAAI. Dr. Wen received the 2026 Graduate Student Mentoring Award\ , 2025 Research Young Faculty Award (Runner-Up)\, and 2022 Early-Career Te aching Excellence Award from NTU. He received the 2026 Advanced Imaging Ea rly Career Award from CIOP\, and 2023 IEEE VSPC Rising Star (Runner-Up) fr om IEEE VSCP. He received the Best Paper Awards at IEEE ICIEA 2023 and IEE E MIPR 2023\, and Best Paper Award (Runner-Up) from IEEE ICME 2020. He has been ranked among the World Top 2% Scientists in Artificial Intelligence by Stanford University and the Top 0.05% Highly Cited Scholar by ScholarGP S.</div> END:VEVENT END:VCALENDAR