BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Robotics Institute Carnegie Mellon University - ECPv6.15.12.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Robotics Institute Carnegie Mellon University
X-ORIGINAL-URL:https://www.ri.cmu.edu
X-WR-CALDESC:Events for Robotics Institute Carnegie Mellon University
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20250309T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20251102T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20260308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20261101T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20270314T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20271107T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260930T160000
DTEND;TZID=America/New_York:20260930T170000
DTSTAMP:20261009T081824
CREATED:20261001T142902Z
LAST-MODIFIED:20261001T142902Z
UID:153867-1790784000-1790787600@www.ri.cmu.edu
SUMMARY:RI PhD Speaking Qual - Jianjin Xu
DESCRIPTION:Date: Wednesday\, Sep 30\, 2026Time: 16:00 – 17:00 PMLocation: NSH 4305Zoom: https://cmu.zoom.us/j/97595860992?pwd=voNXd0zhn8HdqFakFOF3At8y0NbydV.1Title: Efficient 3D Avatar Reconstruction with Geometric Guidance \nAbstract:3D animatable human avatars are widely used in film making\, game characters\, and telepresence. To create these avatars efficiently\, researchers propose to reconstruct the avatar from several input images with a feedforward network. These networks are mostly transformers trained with large proprietary data and thousands of H100 GPU hours. However\, do we really need such a scale of data and compute for this task? \nOur answer is no. In this talk\, we present ARG-Avatar\, a lightweight network with only 68M trainable parameters\, yet achieves SOTA performance on OOD testing data with 13x less training compute to the best baseline. We will go through the two core components of ARG-Avatar. The first is FACRoPE\, which inject geometric guidance into the attention with RoPE mechanism. We propose a novel coordinate formulation named Foreground Avatar Coordinates (FAC)\, to associate let the network tokens focus on its corresponding image regions. The second is Intermediate Token Rendering (ITR)\, which decodes a coarse avatar from intermediate network tokens during forward pass. We show that these components are all beneficial in the ablation study. In conclusion\, we show that by properly injecting geometric into attention\, we make an architecture that learns more efficiently and effectively for feedforward avatar reconstruction. \n\n—\n \n\nBest regards\, \nJianjin Xu.\nCarnegie Mellon University\, Ph.D. in Robotics\nhttps://atlantixjj.github.io/
URL:https://www.ri.cmu.edu/event/ri-phd-speaking-qual-jianjin-xu/
LOCATION:Newell-Simon Hall 4305
CATEGORIES:PhD Speaking Qualifier,Student Talks
END:VEVENT
END:VCALENDAR