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 (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:Technical Papers\n\nEach Paper gives a 10 minute presentation.
 \n\nGaussianObject: High-Quality 3D Object Reconstruction from Four Views 
 with Gaussian Splatting\n\nReconstructing and rendering 3D objects from hi
 ghly sparse views is of critical importance for promoting applications of 
 3D vision techniques and improving user experience. However, images from s
 parse views only contain very limited 3D information, leading to two signi
 ficant challenges: 1) Difficult...\n\n\nChen Yang and Sikuang Li (Shanghai
  Jiao Tong University), Jiemin Fang (Huawei), Ruofan Liang (University of 
 Toronto), Lingxi Xie and Xiaopeng Zhang (Huawei), Wei Shen (Shanghai Jiao 
 Tong University), and Qi Tian (Huawei)\n---------------------\nReal-time L
 arge-scale Deformation of Gaussian Splatting\n\nNeural implicit representa
 tions, including Neural Distance Fields and Neural Radiance Fields, have d
 emonstrated significant capabilities for reconstructing surfaces with comp
 licated geometry and topology, and generating novel views of a scene. Neve
 rtheless, it is challenging for users to directly de...\n\n\nLin Gao (Inst
 itute of Computing Technology, Chinese Academy of Sciences; 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 of Sciences; University
  of Chinese Academy of Sciences); Hongbo Fu (Hong Kong University of Scien
 ce and Technology); and Yu-Kun Lai (Cardiff University)\n-----------------
 ----\nBlobGEN-3D: Compositional 3D-Consistent Freeview Image Generation wi
 th 3D Blobs\n\nRecent advances in text-to-image diffusion models have sign
 ificantly enhanced image generation quality, when trained on internet-scal
 e data. However, existing methods are constrained by their reliance on ima
 ge or scene-level conditions, limiting their ability to synthesize composa
 ble 3D objects in a...\n\n\nChao Liu, Weili Nie, Sifei Liu, Abhishek Badki
 , Hang Su, Morteza Mardani, Benjamin Eckart, and Arash Vahdat (NVIDIA)\n--
 -------------------\nL3DG: Latent 3D Gaussian Diffusion\n\nWe propose L3DG
 , the first approach for generative 3D modeling of 3D Gaussians through a 
 latent 3D Gaussian diffusion formulation.\nThis enables effective generati
 ve 3D modeling, scaling to generation of entire room-scale scenes which ca
 n be very efficiently rendered.\nTo enable effective synthesis of...\n\n\n
 Barbara Roessle (Technical University of Munich); Norman Müller, Lorenzo P
 orzi, Samuel Rota Bulò, and Peter Kontschieder (Meta Reality Labs); and An
 gela Dai and Matthias Nießner (Technical University of Munich)\n----------
 -----------\n3DGSR: Implicit Surface Reconstruction with 3D Gaussian Splat
 ting\n\nIn this paper, we present an implicit surface reconstruction metho
 d with\n3D Gaussian Splatting (3DGS), namely 3DGSR, that allows for accura
 te 3D\nreconstruction with intricate details while inheriting the high eff
 iciency and\nrendering quality of 3DGS. The key insight is to incorporate 
 an implicit\nsig...\n\n\nXiaoyang Lyu, Yang-Tian Sun, Yi-Hua Huang, Xiuzhe
  Wu, and Ziyi Yang (University of Hong Kong); Yilun Chen and Jiangmiao Pan
 g (Shanghai Artificial Intelligence Laboratory); and Xiaojuan Qi (Universi
 ty of Hong Kong)\n---------------------\nEVSplitting: An Efficient and Vis
 ually Consistent Splitting Algorithm for 3D Gaussian Splatting\n\nThis pap
 er presents EVSplitting, an efficient and visually consistent splitting al
 gorithm for 3D Gaussian Splatting (3DGS). It is designed to make operating
  3DGS as easy and effective as other 3D explicit representations, readily 
 for industrial productions. The challenges of above target 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 Technology, Tsinghua Unive
 rsity); Ralph Martin (School of Computer Science and Informatics, Cardiff 
 University); and Shi-Min Hu (BNRist, Department of Computer Science and Te
 chnology, Tsinghua University)\n\nRegistration Category: Full Access, Full
  Access Supporter\n\nLanguage Format: English Language\n\nSession Chair: P
 eng-Shuai Wang (Peking University)
END:VEVENT
END:VCALENDAR