BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//UM//UM*Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Detroit
TZURL:http://tzurl.org/zoneinfo/America/Detroit
X-LIC-LOCATION:America/Detroit
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20070311T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20071104T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251201T084949
DTSTART;TZID=America/Detroit:20251203T080000
DTEND;TZID=America/Detroit:20251203T100000
SUMMARY:Presentation:Leveraging 3D Geometry for Place Recognition and Image Restoration in Visual and Thermal SLAM
DESCRIPTION:Committee Chair:  Katherine Skinner\n\nAbstract:\nSimultaneous Localization and Mapping (SLAM) is the task of progressively mapping a sensor platform's surroundings\, while also tracking its pose (position and orientation) within it. SLAM enables robot navigation in unseen\, unstructured\, and GPS-denied environments and supports virtual and augmented reality applications without requiring external sensors or fiducials. Due to the low cost\, weight\, and power consumption\, small size\, and high spatial resolution of visible spectrum cameras\, visual SLAM is especially well-studied. However\, visual SLAM is challenged by image degradation arising from poor illumination and visual obscurants such as rain\, fog\, snow\, dust\, and smoke. Thermal cameras offer an alternative that can operate in complete darkness and see through the aforementioned visual obscurants\, but only relatively low quality uncooled microbolometer thermal cameras are practical in most applications. Due to the physics of microbolometer image formation\, SLAM with these cameras must often contend with significant motion blur\, rolling shutter distortions\, and noise. Additionally\, all forms of SLAM are fundamentally susceptible to pose drift\, which is error accumulated by concatenating relative pose estimates. The problems of pose drift and image degradation can be mitigated with place recognition and image restoration. In recent years\, both tasks are commonly performed with end-to-end deep learning approaches that process only one image or a small set of images at a time. However\, these methods fail to exploit the full extent of information available in the context of SLAM and are limited in their ability to generalize to scenarios unrepresented in their training data.\n\nThis thesis introduces techniques for place recognition and image restoration that leverage 3D geometry that is either freely available as a byproduct of SLAM or can be jointly estimated. By utilizing estimated 3D geometry\, these methods implicitly exploit wide baseline multi-view information and\, if available\, data from multiple sensors. First\, an autonomous vehicle dataset is introduced featuring challenging conditions\, including adverse illumination and opposing viewpoints\, captured by stereo RGB\, monochrome\, event\, and thermal cameras. Next\, a place recognition algorithm for similar and opposing viewpoints is introduced that forms descriptors from point clouds estimated through stereo visual odometry. The approach is evaluated on the new dataset and achieves high performance in many conditions\, except poorly lit areas at night where the surrounding structure cannot be perceived. This highlights a potential use case for thermal SLAM. Then\, towards robust thermal SLAM\, an approach for thermal image restoration is proposed that incorporates the unique image formation model of microbolometer thermal cameras with Neural Radiance Fields (NeRFs). Finally\, the rendering pipeline introduced for thermal image restoration is adapted to 3D Gaussian Splatting and integrated into a thermal-inertial SLAM system uniquely capable of operating under severe thermal image degradation. Overall\, the methods proposed in this thesis demonstrate the potential of leveraging 3D geometry in all components of a SLAM system and contribute to making SLAM reliable in challenging conditions and large-scale environments.\n\nZoom passcode: slam
UID:142274-21890324@events.umich.edu
URL:https://events.umich.edu/event/142274
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Robotics,Michigan Robotics
LOCATION:Ford Robotics Building - 2300
CONTACT:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20251114T111221
DTSTART;TZID=America/Detroit:20251203T080000
DTEND;TZID=America/Detroit:20251203T235900
SUMMARY:Other:Nam Center for Korean Studies Mascot Design Contest
DESCRIPTION:📣 Announcing the Nam Center for Korean Studies Mascot Contest! 📣\n\nAre you creative\, passionate about Korean culture\, or someone who loves bringing people together? Help us design the Nam Center’s very first mascot! We invite students\, faculty\, staff\, and community members to submit ideas that celebrate Korea’s vibrant spirit and culture\, as well as the mission of the Nam Center.\n\nHow to Enter:\nAnyone regardless of their affiliation and age can enter the contest! Submit your original mascot design (sketch\, painting\, or digital art)\, along with a brief description of your mascot’s personality and meaning [https://myumi.ch/4mEjZ].\n\nDeadline for Entries: December 10\, 11:59 PM (EST)\, 2025\n\nWinner Announcement: Winners will be officially announced on December 21 on our Facebook page and notified via email.\n\nPrizes: \n🥇 First Place: Your design will become the official Nam Center mascot! You’ll receive either a custom 6-inch plush keychain or a larger plush (based on your design)\, along with a $250 gift card.\n🥈 Second Place: Honorable mention\, Nam Center tote bag\, and a $100 gift card.\n🥉 Third Place: Recognition\, Nam Center tote bag\, and a $50 gift card.\nPrizes will be mailed to you.\n\n⭐ Rules & Submission ⭐\n - Submit one mascot character drawing (.jpg or .png file / maximum file size 20 MB)\n - Your design should be truly original and represent the vibrant Nam Center for Korean Studies.\n - Each entrant can submit only one design.\n - Your creation must be entirely your own—and exclusively yours!\n - Designs must not have been previously published.\n - No existing logos\, brands\, or unauthorized third-party images.\n - You may add a creative emblem with “Nam Center\,” “Nam Center for Korean Studies\,” or “NCKS” to your design! It could be featured in future Nam Center promos.\n - A caption giving your mascot a name and a personality—tell us what inspired your design! \n - By entering\, you’ll confirm that you’ve read and agree to the terms outlined on the contest page.\n\n🏆 Winner Selection 🏆\nAfter the deadline\, a panel of judges from the Nam Center and the U-M International Institute will review your brilliant entries! They’ll be looking for:\n - Outstanding originality and creativity\n - A compelling connection to the Nam Center’s culture and mission\n - Clarity and quality in the design\n - Overall impact\n\nConditions: \n - Winners will be contacted by email and need to reply within 7 business days. If we don’t hear back\, another winner may be chosen.\n - Judges may request minor tweaks for the winning design. You’ll have 10 days to review and approve any changes.\n - If we don’t receive enough high-quality entries\, we may extend the deadline or decide not to select a winner.\n\nUnleash your creativity and show us the heart of the Nam Center! Good luck and have fun! ⭐\n\nFor questions\, please contact outreachkorea@umich.edu.
UID:141870-21889572@events.umich.edu
URL:https://events.umich.edu/event/141870
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Korea,Korean Studies,Asian Languages And Cultures,Art,animation
LOCATION:Off Campus Location
CONTACT:
END:VEVENT
END:VCALENDAR