BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250110T023313Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241206T104500
DTEND;TZID=Asia/Tokyo:20241206T115500
UID:siggraphasia_SIGGRAPH Asia 2024_sess143@linklings.com
SUMMARY:My Name is Carl: Gaussian Humans
DESCRIPTION:Technical Papers\n\nEach Paper gives a 10 minute presentation.
 \n\nGaussianHeads: End-to-End Learning of Drivable Gaussian Head Avatars f
 rom Coarse-to-fine Representations\n\nReal-time rendering of human head av
 atars is a cornerstone of many computer graphics applications, such as aug
 mented reality, video games, and films, to name a few. Recent approaches a
 ddress this challenge with computationally efficient geometry primitives i
 n a carefully calibrated multi-view setup....\n\n\nKartik Teotia (Max Plan
 ck Institute for Informatics, Saarland Informatics Campus); Hyeongwoo Kim 
 (Imperial College London); Pablo Garrido (Flawless AI); Marc Habermann (Ma
 x Planck Institute for Informatics, Saarland Informatics Campus); Mohamed 
 Elgharib (Max Planck Institute for Informatics); and Christian Theobalt (M
 ax Planck Institute for Informatics, Saarland Informatics Campus)\n-------
 --------------\nGGHead: Fast and Generalizable 3D Gaussian Heads\n\nLearni
 ng 3D head priors from large 2D image collections is an important step tow
 ards high-quality 3D-aware human modeling. \nA core requirement is an effi
 cient architecture that scales well to large-scale datasets and large imag
 e resolutions. \nUnfortunately, existing 3D GANs struggle to scale to gene
 ...\n\n\nTobias Kirschstein, Simon Giebenhain, and Jiapeng Tang (Technical
  University of Munich); Markos Georgopoulos (Independent); and Matthias Ni
 eßner (Technical University of Munich)\n---------------------\nRobust Dual
  Gaussian Splatting for Immersive Human-centric Volumetric Videos\n\nVolum
 etric video represents a transformative advancement in visual media, enabl
 ing users to freely navigate immersive virtual experiences and narrowing t
 he gap between digital and real worlds. However, the need for extensive ma
 nual intervention to stabilize mesh sequences and the generation of exces.
 ..\n\n\nYuheng Jiang, Zhehao Shen, Yu Hong, Chengcheng Guo, and Yize Wu (S
 hanghaiTech University); Yingliang Zhang (DGene Inc.); and Jingyi Yu and L
 an Xu (ShanghaiTech University)\n---------------------\nGaussian Surfel Sp
 latting for Live Human Performance Capture\n\nHigh-quality real-time rende
 ring using user-affordable capture rigs is an essential property of human 
 performance capture systems for real-world applications. However, state-of
 -the-art performance capture methods may not yield satisfactory rendering 
 results under a very sparse (e.g., four) capture s...\n\n\nZheng Dong (Sta
 te Key Laboratory of CAD&CG, Zhejiang University); Ke Xu (City University 
 of Hong Kong); Yaoan Gao, Hujun Bao, and Weiwei Xu (State Key Laboratory o
 f CAD&CG, Zhejiang University); and Rynson W.H. Lau (City University of Ho
 ng Kong)\n---------------------\nNPGA: Neural Parametric Gaussian Avatars\
 n\nThe creation of high-fidelity, digital versions of human heads is an im
 portant stepping stone in the process of further integrating virtual compo
 nents into our everyday lives. Constructing such avatars is a challenging 
 research problem, due to a high demand for photo-realism and real-time ren
 dering ...\n\n\nSimon Giebenhain and Tobias Kirschstein (Technical Univers
 ity of Munich); Martin Rünz (Synthesia); Lourdes Agapito (University Colle
 ge London (UCL), Synthesia); and Matthias Nießner (Technical University of
  Munich, Synthesia)\n---------------------\nURAvatar: Universal Relightabl
 e Gaussian Codec Avatars\n\nWe present a new approach to creating photorea
 listic and relightable head avatars from a phone scan with unknown illumin
 ation. The reconstructed avatars can be animated and relit in real time wi
 th the global illumination of diverse environments. Unlike existing approa
 ches that estimate parametric re...\n\n\nJunxuan Li, Chen Cao, Gabriel Sch
 wartz, Rawal Khirodkar, Christian Richardt, Tomas Simon, Yaser Sheikh, and
  Shunsuke Saito (Reality Labs Research)\n\nRegistration Category: Full Acc
 ess, Full Access Supporter\n\nLanguage Format: English Language\n\nSession
  Chair: Iain Matthews (Epic Games, Carnegie Mellon University)
END:VEVENT
END:VCALENDAR