BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Department of Electrical and Computer Engineering (HKUECE) 電機與計算機工程系 - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://ece.hku.hk
X-WR-CALDESC:Events for Department of Electrical and Computer Engineering (HKUECE) 電機與計算機工程系
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:HKT
DTSTART:20240101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Asia/Hong_Kong:20250502T100000
DTEND;TZID=Asia/Hong_Kong:20250502T110000
DTSTAMP:20260511T230032
CREATED:20250603T024005Z
LAST-MODIFIED:20250603T024005Z
UID:111459-1746180000-1746183600@ece.hku.hk
SUMMARY:Seeing Beyond Limits: Filling the Dimensionality and Visibility Gaps via the Co-design of Imaging Systems and AI Algorithms
DESCRIPTION:Mode: Online via Zoom\nMeeting ID: 944 3088 8970 | Password: 933450 \nAbstract\nConventional imaging systems face inherent dimensionality and visibility limits\, primarily because image sensors are typically two-dimensional\, and light tends to diffuse on rough surfaces or scatter within complex media. In this talk\, I will reframe imaging systems through the lens of optical encoding and neural decoding\, presenting my key contributions aimed at transcending the traditional limits of dimensionality and visibility. First\, I introduce Snapshot Compressive Imaging (SCI)\, which encodes multiple temporal\, spectral\, or angular frames into a single measurement captured by a standard two-dimensional sensor. By learning high-dimensional visual priors from image or video data\, we can efficiently reconstruct the original higher-dimensional data cube at scale. Second\, I present Privacy Dual Imaging (PDI)\, which leverages ambient light sensors embedded in most smart devices to capture images of the scene in front of the screen. This idea of seeing the invisible from subtle intensity fluctuations is inspired by George Orwell’s novel 1984\, wherein Big Brother is watching you through a two-way telescreen\, and it closely relates to incoherent lensless imaging and non-line-of-sight imaging. Lastly\, I show that large AI models\, particularly diffusion models\, can serve as generic visual priors for both cases and beyond. I aim to push the boundaries of imaging and sensing within relevant domains of AI for science and healthcare (with an example). \nSpeaker\nMr. Yang LIU\nComputer Science & Artificial Intelligence Laboratory\,\nDepartment of Electrical Engineering and Computer Science\,\nMassachusetts Institute of Technology \nSpeaker’s Biography\nYang LIU is a final-year PhD student working on AI for Imaging and AI for Science in general at MIT EECS and CSAIL with Prof. Fredo Durand. He is excited about seeing\, making\, and connecting (almost) anything. He emphasizes the co-design of AI algorithms and hardware systems for imaging and sensing beyond the native capability of visual sensors. His work has been published on top venues including Nature Materials\, Science Advances\, IEEE TPAMI\, CVPR\, and OSA Photonics Research; featured on Forbes\, WIRED\, Fox News\, and Ars Technica; contributed to a W3C working draft. He is an MIT Presidential Fellow and a Takeda Fellow. \nOrganiser\nProf. Kaibin HUANG\nDepartment of Electrical and Electronic Engineering\,\nThe University of Hong Kong \nAll are welcome!
URL:https://ece.hku.hk/events/20250502-1/
LOCATION:Online via Zoom
CATEGORIES:Seminar
ATTACH;FMTTYPE=image/jpeg:https://ece.hku.hk/wp-content/uploads/2025/06/1280.jpg
END:VEVENT
END:VCALENDAR