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:20251124T150000
DTEND;TZID=Asia/Hong_Kong:20251124T160000
DTSTAMP:20260511T154001
CREATED:20251118T042520Z
LAST-MODIFIED:20251118T042520Z
UID:113922-1763996400-1764000000@ece.hku.hk
SUMMARY:RPG Seminar – Event-augmented 3D Geometry Estimation for Extreme Conditions
DESCRIPTION:Zoom Link: https://hku.zoom.us/meetings/92032873265/invitations?signature=ZlnhYyZi056expgN41HYZdcENW6INTs0MyPEhyhl7r8 \nAbstract\nRobust 3D geometry estimation from videos is essential for autonomous navigation\, SLAM\, and 3D reconstruction. While recent pointmap-based methods such as DUSt3R enable accurate pose-free reconstruction\, RGB-only approaches remain fragile under dynamic scenes and extreme illumination. We introduce a geometry estimation framework that augments pointmap reconstruction with asynchronous event data. It features: (1) a retinex-inspired enhancement module and a lightweight event adapter with SNR-aware fusion for adaptive RGB–event integration; and (2) an event-based photometric consistency loss that enforces spatiotemporal coherence during global optimization. Our method delivers robust geometry estimation in dynamic\, low-light environments without night-time retraining\, achieving substantial gains over state-of-the-art RGB-only baselines on monocular depth\, video depth\, and pose tracking.\n \nSpeaker\nMr. Yifei YU\nDepartment of Electrical and Electronic Engineering\nThe University of Hong Kong \nBiography of the Speaker\nYU Yifei received B.E degree from School of Information Science and Technology\, Fudan University\, Shanghai\, China\, in 2022. He is currently pursuing the Ph.D. degree with the Department of Electrical and Electronic Engineering under the supervision of Prof. Xiaojuan Qi. His research interests mainly include in-memory computing\, 3D vision\, neuromorphic computing\, and software-hardware co-design. \nOrganiser\nProf. Xiaojuan Qi\nDepartment of Electrical and Electronic Engineering\, The University of Hong Kong \nAll are welcome.
URL:https://ece.hku.hk/events/20251124/
LOCATION:Online via Zoom
CATEGORIES:Seminar
ATTACH;FMTTYPE=image/jpeg:https://ece.hku.hk/wp-content/uploads/2024/11/rpg-seminar.jpg
END:VEVENT
END:VCALENDAR