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:20260817T171535Z
LOCATION:Hall B5 (1)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241204T130000
DTEND;TZID=Asia/Tokyo:20241204T141000
UID:siggraphasia_SIGGRAPH Asia 2024_sess115@linklings.com
SUMMARY:Splats and Blobs: Generate, Deform, Diffuse
DESCRIPTION:Each Paper gives a 10 minute presentation.\n\nEVSplitting: An 
 Efficient and Visually Consistent Splitting Algorithm for 3D Gaussian Spla
 tting\n\nThis paper presents EVSplitting, an efficient and visually consis
 tent splitting algorithm for 3D Gaussian Splatting (3DGS). It is designed 
 to make operating 3DGS as easy and effective as other 3D explicit represen
 tations, readily for industrial productions. The challenges of above targe
 t are: 1) The...\n\n\nQi-Yuan Feng, Geng-Chen Cao, Hao-Xiang Chen, Qun-Ce 
 Xu, and Tai-Jiang Mu (BNRist, Department of Computer Science and Technolog
 y, Tsinghua University); Ralph Martin (School of Computer Science and Info
 rmatics, Cardiff University); and Shi-Min Hu (BNRist, Department of Comput
 er Science and Technology, Tsinghua University)\n---------------------\n3D
 GSR: Implicit Surface Reconstruction with 3D Gaussian Splatting\n\nIn this
  paper, we present an implicit surface reconstruction method with\n3D Gaus
 sian Splatting (3DGS), namely 3DGSR, that allows for accurate 3D\nreconstr
 uction with intricate details while inheriting the high efficiency and\nre
 ndering quality of 3DGS. The key insight is to incorporate an implicit\nsi
 g...\n\n\nXiaoyang Lyu, Yang-Tian Sun, Yi-Hua Huang, Xiuzhe Wu, and Ziyi Y
 ang (University of Hong Kong); Yilun Chen and Jiangmiao Pang (Shanghai Art
 ificial Intelligence Laboratory); and Xiaojuan Qi (University of Hong Kong
 )\n---------------------\nGaussianObject: High-Quality 3D Object Reconstru
 ction from Four Views with Gaussian Splatting\n\nReconstructing and render
 ing 3D objects from highly sparse views is of critical importance for prom
 oting applications of 3D vision techniques and improving user experience. 
 However, images from sparse views only contain very limited 3D information
 , leading to two significant challenges: 1) Difficult...\n\n\nChen Yang an
 d Sikuang Li (Shanghai Jiao Tong University), Jiemin Fang (Huawei), Ruofan
  Liang (University of Toronto), Lingxi Xie and Xiaopeng Zhang (Huawei), We
 i Shen (Shanghai Jiao Tong University), and Qi Tian (Huawei)\n------------
 ---------\nReal-time Large-scale Deformation of Gaussian Splatting\n\nNeur
 al implicit representations, including Neural Distance Fields and Neural R
 adiance Fields, have demonstrated significant capabilities for reconstruct
 ing surfaces with complicated geometry and topology, and generating novel 
 views of a scene. Nevertheless, it is challenging for users to directly de
 ...\n\n\nLin Gao (Institute of Computing Technology, Chinese Academy of Sc
 iences; University of Chinese Academy of Sciences); Jie Yang (Institute of
  Computing Technology, Chinese Academy of Sciences); Bo-Tao Zhang, Jia-Mu 
 Sun, and Yu-Jie Yuan (Institute of Computing Technology, Chinese Academy o
 f Sciences; University of Chinese Academy of Sciences); Hongbo Fu (Hong Ko
 ng University of Science and Technology); and Yu-Kun Lai (Cardiff Universi
 ty)\n---------------------\nBlobGEN-3D: Compositional 3D-Consistent Freevi
 ew Image Generation with 3D Blobs\n\nRecent advances in text-to-image diff
 usion models have significantly enhanced image generation quality, when tr
 ained on internet-scale data. However, existing methods are constrained by
  their reliance on image or scene-level conditions, limiting their ability
  to synthesize composable 3D objects in a...\n\n\nChao Liu, Weili Nie, Sif
 ei Liu, Abhishek Badki, Hang Su, Morteza Mardani, Benjamin Eckart, and Ara
 sh Vahdat (NVIDIA)\n---------------------\nL3DG: Latent 3D Gaussian Diffus
 ion\n\nWe propose L3DG, the first approach for generative 3D modeling of 3
 D Gaussians through a latent 3D Gaussian diffusion formulation.\nThis enab
 les effective generative 3D modeling, scaling to generation of entire room
 -scale scenes which can be very efficiently rendered.\nTo enable effective
  synthesis of...\n\n\nBarbara Roessle (Technical University of Munich); No
 rman Müller, Lorenzo Porzi, Samuel Rota Bulò, and Peter Kontschieder (Meta
  Reality Labs); and Angela Dai and Matthias Nießner (Technical University 
 of Munich)\n\nRegistration Category: Full Access, Full Access Supporter\n\
 nLanguage Format: English Language\n\nSession Chair: Peng-Shuai Wang (Peki
 ng University)
END:VEVENT
END:VCALENDAR