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:20260817T171536Z
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:Each Paper gives a 10 minute presentation.\n\nGaussian Surfel 
 Splatting for Live Human Performance Capture\n\nHigh-quality real-time ren
 dering using user-affordable capture rigs is an essential property of huma
 n performance capture systems for real-world applications. However, state-
 of-the-art performance capture methods may not yield satisfactory renderin
 g results under a very sparse (e.g., four) capture s...\n\n\nZheng Dong (S
 tate Key Laboratory of CAD&CG, Zhejiang University); Ke Xu (City Universit
 y of Hong Kong); Yaoan Gao, Hujun Bao, and Weiwei Xu (State Key Laboratory
  of CAD&CG, Zhejiang University); and Rynson W.H. Lau (City University of 
 Hong Kong)\n---------------------\nGaussianHeads: End-to-End Learning of D
 rivable Gaussian Head Avatars from Coarse-to-fine Representations\n\nReal-
 time rendering of human head avatars is a cornerstone of many computer gra
 phics applications, such as augmented reality, video games, and films, to 
 name a few. Recent approaches address this challenge with computationally 
 efficient geometry primitives in a carefully calibrated multi-view setup..
 ..\n\n\nKartik Teotia (Max Planck Institute for Informatics, Saarland Info
 rmatics Campus); Hyeongwoo Kim (Imperial College London); Pablo Garrido (F
 lawless AI); Marc Habermann (Max Planck Institute for Informatics, Saarlan
 d Informatics Campus); Mohamed Elgharib (Max Planck Institute for Informat
 ics); and Christian Theobalt (Max Planck Institute for Informatics, Saarla
 nd Informatics Campus)\n---------------------\nGGHead: Fast and Generaliza
 ble 3D Gaussian Heads\n\nLearning 3D head priors from large 2D image colle
 ctions is an important step towards high-quality 3D-aware human modeling. 
 \nA core requirement is an efficient architecture that scales well to larg
 e-scale datasets and large image resolutions. \nUnfortunately, existing 3D
  GANs struggle to scale to gene...\n\n\nTobias Kirschstein, Simon Giebenha
 in, and Jiapeng Tang (Technical University of Munich); Markos Georgopoulos
  (Independent); and Matthias Nießner (Technical University of Munich)\n---
 ------------------\nRobust Dual Gaussian Splatting for Immersive Human-cen
 tric Volumetric Videos\n\nVolumetric video represents a transformative adv
 ancement in visual media, enabling users to freely navigate immersive virt
 ual experiences and narrowing the gap between digital and real worlds. How
 ever, the need for extensive manual intervention to stabilize mesh sequenc
 es and the generation of exces...\n\n\nYuheng Jiang, Zhehao Shen, Yu Hong,
  Chengcheng Guo, and Yize Wu (ShanghaiTech University); Yingliang Zhang (D
 Gene Inc.); and Jingyi Yu and Lan Xu (ShanghaiTech University)\n----------
 -----------\nNPGA: Neural Parametric Gaussian Avatars\n\nThe creation of h
 igh-fidelity, digital versions of human heads is an important stepping sto
 ne in the process of further integrating virtual components into our every
 day lives. Constructing such avatars is a challenging research problem, du
 e to a high demand for photo-realism and real-time rendering ...\n\n\nSimo
 n Giebenhain and Tobias Kirschstein (Technical University of Munich); Mart
 in Rünz (Synthesia); Lourdes Agapito (University College London (UCL), Syn
 thesia); and Matthias Nießner (Technical University of Munich, Synthesia)\
 n---------------------\nURAvatar: Universal Relightable Gaussian Codec Ava
 tars\n\nWe present a new approach to creating photorealistic and relightab
 le head avatars from a phone scan with unknown illumination. The reconstru
 cted avatars can be animated and relit in real time with the global illumi
 nation of diverse environments. Unlike existing approaches that estimate p
 arametric re...\n\n\nJunxuan Li, Chen Cao, Gabriel Schwartz, Rawal Khirodk
 ar, Christian Richardt, Tomas Simon, Yaser Sheikh, and Shunsuke Saito (Rea
 lity Labs Research)\n\nRegistration Category: Full Access, Full Access Sup
 porter\n\nLanguage Format: English Language\n\nSession Chair: Iain Matthew
 s (Epic Games, Carnegie Mellon University)
END:VEVENT
END:VCALENDAR