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:20250110T023309Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241203T130000
DTEND;TZID=Asia/Tokyo:20241203T141000
UID:siggraphasia_SIGGRAPH Asia 2024_sess104@linklings.com
SUMMARY:Going Big in Rendering
DESCRIPTION:Technical Papers\n\nEach Paper gives a 10 minute presentation.
 \n\nTaming 3DGS: High-Quality Radiance Fields with Limited Resources\n\n3D
  Gaussian Splatting (3DGS) has transformed novel-view synthesis with its f
 ast, interpretable, and high-fidelity rendering. However, its resource req
 uirements limit its usability: Especially on weaker or constrained devices
 , training performance degrades quickly and often cannot complete due to e
 xc...\n\n\nSaswat Subhajyoti Mallick (Carnegie Mellon University); Rahul G
 oel (International Institute of Information Technology, Hyderabad); Bernha
 rd Kerbl (Carnegie Mellon University); Markus Steinberger (Graz University
  of Technology); and Francisco Vicente Carrasco and Fernando De La Torre (
 Carnegie Mellon University)\n---------------------\nInfNeRF: Towards Infin
 ite Scale NeRF Rendering with O(log n) Space Complexity\n\nThe conventiona
 l mesh-based Level of Detail (LoD) technique, exemplified by applications 
 such as Google Earth and many game engines, exhibits the capability to hol
 istically represent a large scene even the Earth, and achieves rendering w
 ith a space complexity of O(log n).\nThis constrained data requi...\n\n\nJ
 iabin Liang and Lanqing Zhang (Sea AI Lab), Zhuoran Zhao (National Univers
 ity of Singapore), and Xiangyu Xu (Xi'an Jiaotong University)\n-----------
 ----------\nMVImgNet2.0: A Larger-scale Dataset of Multi-view Images\n\nMV
 ImgNet is a large-scale dataset that contains multi-view images of ~220k r
 eal-world objects in 238 classes. As a counterpart of ImageNet, it introdu
 ces 3D visual signals via multi-view shooting, making a soft bridge betwee
 n 2D and 3D vision. This paper constructs the MVImgNet2.0 dataset that exp
 an...\n\n\nXiaoguang Han (SSE, The Chinese University of Hong Kong, Shenzh
 en; FNii, The Chinese University of Hong Kong, Shenzhen); Yushuang Wu, Luy
 ue Shi, Haolin Liu, Hongjie Liao, and Lingteng Qiu (FNii, The Chinese Univ
 ersity of Hong Kong, Shenzhen; SSE, The Chinese University of Hong Kong, S
 henzhen); Weihao Yuan, Xiaodong Gu, and Zilong Dong (Alibaba); and Shuguan
 g Cui (SSE, The Chinese University of Hong Kong, Shenzhen; FNii, The Chine
 se University of Hong Kong, Shenzhen)\n---------------------\nRepresenting
  Long Volumetric Video with Temporal Gaussian Hierarchy\n\nThis paper aims
  to address the challenge of reconstructing long volumetric videos from mu
 lti-view RGB videos.\nRecent dynamic view synthesis methods leverage power
 ful 4D representations, like feature grids or point cloud sequences, to ac
 hieve high-quality rendering results. However, they are typicall...\n\n\nZ
 hen Xu (State Key Laboratory of CAD&CG, Zhejiang University; Zhejiang Univ
 ersity); Yinghao Xu (Stanford University); Zhiyuan Yu (Department of Mathe
 matics, Hong Kong University of Science and Technology); Sida Peng and Jia
 ming Sun (Zhejiang University); and Hujun Bao and Xiaowei Zhou (State Key 
 Laboratory of CAD&CG, Zhejiang University)\n---------------------\nLetsGo:
  Large-Scale Garage Modeling and Rendering via LiDAR-Assisted Gaussian Pri
 mitives\n\nLarge garages are ubiquitous yet intricate scenes that present 
 unique challenges due to their monotonous colors, repetitive patterns, ref
 lective surfaces, and transparent vehicle glass. Conventional Structure fr
 om Motion (SfM) methods for camera pose estimation and 3D reconstruction o
 ften fail in th...\n\n\nJiadi Cui (ShanghaiTech University, Stereye Inc.);
  Junming Cao (Shanghai Advanced Research Institute, Chinese Academy of Sci
 ences; University of Chinese Academy of Sciences); Fuqiang Zhao (ShanghaiT
 ech University, NeuDim Inc.); Zhipeng He and Yifan Chen (ShanghaiTech Univ
 ersity); Yuhui Zhong (DGene Inc.); Lan Xu and Yujiao Shi (ShanghaiTech Uni
 versity); Yingliang Zhang (DGene Inc.); and Jingyi Yu (ShanghaiTech Univer
 sity)\n\nRegistration Category: Full Access, Full Access Supporter\n\nLang
 uage Format: English Language\n\nSession Chair: Bernhard Kerbl (Technical 
 University of Vienna)
END:VEVENT
END:VCALENDAR