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:20250110T023312Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241204T104500
DTEND;TZID=Asia/Tokyo:20241204T115500
UID:siggraphasia_SIGGRAPH Asia 2024_sess113@linklings.com
SUMMARY:Look at it Differently: Novel View Synthesis
DESCRIPTION:Technical Papers\n\nEach Paper gives a 10 minute presentation.
 \n\nCafca: High-quality Novel View Synthesis of Expressive Faces from Casu
 al Few-shot Captures\n\nVolumetric modeling and neural radiance field repr
 esentations have revolutionized 3D face capture and photorealistic novel v
 iew synthesis. However, these methods often require hundreds of multi-view
  input images and are thus inapplicable to cases with less than a handful 
 of inputs.\nWe present a nove...\n\n\nMarcel C. Buehler and Gengyan Li (ET
 H Zürich, Google VR); Erroll Wood, Leonhard Helminger, Xu Chen, Tanmay Sha
 h, Daoye Wang, Stephan Garbin, and Sergio Orts Escolano (Google VR); Otmar
  Hilliges (ETH Zürich); and Dmitry Lagun, Jérémy Riviere, Paulo Gotardo, T
 habo Beeler, Abhimitra Meka, and Kripasindhu Sarkar (Google VR)\n---------
 ------------\nNeural Light Spheres for Implicit Image Stitching and View S
 ynthesis\n\nChallenging to capture, and challenging to display on a cellph
 one screen, the panorama paradoxically remains both a staple and underused
  feature of modern mobile camera applications. In this work we address bot
 h of these challenges with a spherical neural light field model for implic
 it panoramic ima...\n\n\nIlya Chugunov and Amogh Joshi (Princeton Universi
 ty), Kiran Murthy and Francois Bleibel (Google Inc.), and Felix Heide (Pri
 nceton University)\n---------------------\nReN Human: Learning Relightable
  Neural Implicit Surfaces for Animatable Human Rendering\n\nThis work prop
 oses ReN Human, a framework that utilizes sparse or even monocular input v
 ideos to reconstruct a 3D human model represented as a deformable implicit
  neural surface. It decomposes geometry and material, resulting in a relig
 htable, animatable human model that can be rendered with novel v...\n\n\nR
 engan Xie (State Key Laboratory of CAD&CG, Zhejiang University); Kai Huang
  (Institute of Computing Technology, Chinese Academy of Sciences; Zhejiang
  Lab); In-Young Cho (KRAFTON); Sen Yang (Zhejiang Lab); Wei Chen, Hujun Ba
 o, and Wenting Zheng (State Key Laboratory of CAD&CG, Zhejiang University)
 ; Rong Li (Zhejiang University); and Yuchi Huo (State Key Laboratory of CA
 D&CG, Zhejiang University; Zhejiang Lab)\n---------------------\nQuark: Re
 al-time, High-resolution, and General Neural View Synthesis\n\nWe present 
 a novel neural algorithm for performing high-quality, high-resolution, rea
 l-time novel view synthesis. From a sparse set of input RGB images or vide
 os streams, our network both reconstructs the 3D scene and renders novel v
 iews at 1080p resolution at 30fps on an NVIDIA A100. Our feed-forwa...\n\n
 \nJohn Flynn, Michael Broxton, Lukas Murmann, Lucy Chai, Matthew DuVall, C
 lément Godard, Kathryn Heal, Srinivas Kaza, Stephen Lombardi, Xuan Luo, Su
 preeth Achar, Kira Prabhu, Tiancheng Sun, Lynn Tsai, and Ryan Overbeck (Go
 ogle)\n---------------------\nPano2Room: Novel View Synthesis from a Singl
 e Indoor Panorama\n\nRecent single-view 3D AIGC methods have made signific
 ant advancements by leveraging knowledge distilled from extensive 3D objec
 t datasets. However, challenges persist in the synthesis of 3D scenes from
  a single view, primarily due to the complexity of real-world environments
  and the limited availabi...\n\n\nGuo Pu, Yiming Zhao, and Zhouhui Lian (W
 angxuan Institute of Computer Technology, Peking University)\n------------
 ---------\nDynamic Gaussian Marbles for Novel View Synthesis of Casual Mon
 ocular Videos\n\nGaussian splatting has become a popular representation fo
 r novel-view synthesis, exhibiting clear strengths in efficiency, photomet
 ric quality, and compositional edibility. Following its success, many work
 s have extended Gaussians to 4D, showing that dynamic Gaussians maintain t
 hese benefits while a...\n\n\nColton Stearns, Adam Harley, and Mikaela Uy 
 (Stanford University); Florian Dubost and Federico Tombari (Google Researc
 h); and Gordon Wetzstein and Leonidas Guibas (Stanford University)\n\nRegi
 stration Category: Full Access, Full Access Supporter\n\nLanguage Format: 
 English Language\n\nSession Chair: Forrester Cole (Google)
END:VEVENT
END:VCALENDAR