BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260417T190057Z
LOCATION:West Building\, Rooms 211-214
DTSTART;TZID=America/Los_Angeles:20250814T090000
DTEND;TZID=America/Los_Angeles:20250814T103000
UID:siggraph_SIGGRAPH 2025_sess122@linklings.com
SUMMARY:The Shape of You
DESCRIPTION:Relightable Full-Body Gaussian Codec Avatars\n\nWe present the
  first drivable full-body avatar model that reconstructs perceptually real
 istic relightable appearance.\n\n\nShaofei Wang (ETH Zürich); Tomas Simon,
  Igor Santesteban, Timur Bagautdinov, Junxuan Li, Vasu Agrawal, Fabian Pra
 da, Shoou-I Yu, Pace Nalbone, Matt Gramlich, Roman Lubachersky, Chenglei W
 u, Javier Romero, Jason Saragih, and Michael Zollhoefer (Reality Labs Rese
 arch, Meta); Andreas Geiger (University of Tübingen, Tübingen AI Center); 
 Siyu Tang (ETH Zürich); and Shunsuke Saito (Reality Labs Research, Meta)\n
 ---------------------\nEVA: Expressive Virtual Avatars from Multi-view Vid
 eos\n\nIn this work, we introduce Expressive Virtual Avatars (EVA), an act
 or-specific, fully controllable and expressive human avatar framework that
  achieves high-fidelity, lifelike renderings in real-time, while enabling 
 independent control of facial expressions, body movements, and hand gestur
 es.\n\n\nHendrik Junkawitsch, Guoxing Sun, and Heming Zhu (Max Planck Inst
 itute for Informatics) and Christian Theobalt and Marc Habermann (Max Plan
 ck Institute for Informatics; Saarbrücken Research Center for Visual Compu
 ting, Interaction and Artificial Intelligence)\n---------------------\nIns
 tantRestore: Single-Step Personalized Face Restoration with Shared-Image A
 ttention\n\nInstantRestore is a fast, personalized face restoration framew
 ork that uses a single-step diffusion model with an extended self-attentio
 n mechanism to match low-quality image patches to high-quality reference p
 atches. Leveraging implicit correspondences in the denoising network, we e
 fficiently trans...\n\n\nHoward Zhang (Snap, University of California Los 
 Angeles); Yuval Alaluf (Tel Aviv University); Sizhuo Ma (Snap); Achuta Kad
 ambi (University of California Los Angeles); and Jian Wang and Kfir Aberma
 n (Snap)\n---------------------\nThe Shape of You - Interactive Discussion
 \n\nAfter the summary presentations, attendees will participate in an inte
 ractive discussion. Outside the room will be a series of poster boards for
  authors to gather around with the audience. Authors are invited to bring 
 any material related to their paper that could instigate further conversat
 ion such...\n\n---------------------\nMyTimeMachine: Personalized Facial A
 ge Transformation\n\nWe personalize a pre-trained global aging prior using
  50 personal selfies, allowing age regression (de-aging) and age progressi
 on (aging) with high fidelity and identity preservation.\n\n\nLuchao Qi (U
 niversity of North Carolina at Chapel Hill (UNC)), Jiaye Wu (University of
  Maryland College Park), Bang Gong (University of North Carolina Chapel Hi
 ll), Annie Wang (University of North Carolina at Chapel Hill (UNC)), David
  Jacobs (University of Maryland College Park), and Roni Sengupta (Universi
 ty of North Carolina at Chapel Hill (UNC))\n---------------------\nGAIA: G
 enerative Animatable Interactive Avatars with Expression-conditioned Gauss
 ians\n\nWe present GAIA (Generative Animatable Interactive Avatars) for hi
 gh-fidelity 3D head avatar generation. GAIA learns dynamic details with ex
 pression-conditioned Gaussians, while being animatable consistently with a
 n underlying morphable model. With a novel two-branch architecture, GAIA d
 isentangles ...\n\n\nZhengming Yu (Texas A&M University); Tianye Li (NVIDI
 A); Jingxiang Sun (Tsinghua University, NVIDIA); Omer Shapira, Seonwook Pa
 rk, Michael Stengel, and Matthew Chan (NVIDIA); Xin Li and Wenping Wang (T
 exas A&M University); and Koki Nagano and Shalini De Mello (NVIDIA)\n-----
 ----------------\nTeGA: Texture Space Gaussian Avatars for High-Resolution
  Dynamic Head Modeling\n\nBy combining a continuous, UVD tangent space 3DG
 S model with a UNet deformation network while maintaining adaptive densifi
 cation, we present a novel high-detail 3D head avatar model that preserves
  even finer detail like pores and eyelashes at 4K resolution.\n\n\nGengyan
  S. Li (ETH Zürich, Google) and Paulo Gotardo, Timo Bolkart, Stephan Garbi
 n, Kripasindhu Sarkar, Abhimitra Meka, Alexandros Lattas, and Thabo Beeler
  (Google)\n\nInterest Area: Research & Education\n\nRecording: Livestreame
 d, Not Livestreamed, Recorded, Not Recorded\n\nRegistration Category: Full
  Conference, Virtual Access, Thursday\n\nSession Chair: Abhimitra Meka (Go
 ogle)
END:VEVENT
END:VCALENDAR