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:20260817T171538Z
LOCATION:Hall B5 (1)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241206T104500
DTEND;TZID=Asia/Tokyo:20241206T115500
UID:siggraphasia_SIGGRAPH Asia 2024_sess142@linklings.com
SUMMARY:Modeling and Reconstruction
DESCRIPTION:Each Paper gives a 10 minute presentation.\n\nFaçAID: A Transf
 ormer Model for Neuro-Symbolic Facade Reconstruction\n\nWe introduce a neu
 ro-symbolic transformer-based model that converts flat, segmented facade s
 tructures into procedural definitions using a custom-designed split gramma
 r. To facilitate this, we first develop a simple split grammar tailored fo
 r architectural facades and then generate a dataset comprisi...\n\n\nAleks
 ander Plocharski (Warsaw University of Technology, IDEAS NCBR); Jan Swidzi
 nski (IDEAS NCBR); Joanna Porter-Sobieraj (Warsaw University of Technology
 ); and Przemyslaw Musialski (New Jersey Institute of Technology, IDEAS NCB
 R)\n---------------------\nLarge Scale Farm Scene Modeling from Remote Sen
 sing Imagery\n\nIn this paper we propose a scalable framework for large-sc
 ale farm scene modeling that utilizes remote sensing data, specifically sa
 tellite images. Our approach begins by accurately extracting and categoriz
 ing the distributions of various scene elements from satellite images into
  four distinct layer...\n\n\nZhiqi Xiao and Hao Jiang (Institute of Comput
 ing Technology, Chinese Academy of Sciences; University of Chinese Academy
  of Sciences); Zhigang Deng (University of Houston); and Ran Li, Wenwei Ha
 n, and Zhaoqi Wang (Institute of Computing Technology, Chinese Academy of 
 Sciences; University of Chinese Academy of Sciences)\n--------------------
 -\nReconstruct translucent thin objects from photos\n\nThe joint reconstru
 ction of shape and appearance for translucent objects from real-world data
  poses a challenge in computer graphics, especially when dealing with comp
 lex layered materials like leaves or paper. The traditional assumption of 
 diffuse transmittance falls short, and more accurate Monte-...\n\n\nXi Den
 g (Cornell University); Lifan Wu (NVIDIA Research); Bruce Walter (Cornell 
 University); Ravi Ramamoorthi (University of California San Diego, NVIDIA 
 Research); Eugene d'Eon (NVIDIA Research); Steve Marschner (Cornell Univer
 sity, NVIDIA Research); and Andrea Weidlich (NVIDIA Research)\n-----------
 ----------\nDreamUDF: Generating Unsigned Distance Fields from A Single Im
 age\n\nRecent advances in diffusion models and neural implicit surfaces ha
 ve shown promising progress in generating 3D models. However, existing gen
 erative frameworks are limited to closed surfaces, failing to cope with a 
 wide range of commonly seen shapes that have open boundaries. In this work
 , we presen...\n\n\nYu-Tao Liu and Xuan Gao (Institute of Computing Techno
 logy, Chinese Academy of Sciences; University of Chinese Academy of Scienc
 es); Weikai Chen (Tencent Games); Jie Yang (Institute of Computing Technol
 ogy, Chinese Academy of Sciences; University of Chinese Academy of Science
 s); Xiaoxu Meng and Bo Yang (Tencent Games); and Lin Gao (Institute of Com
 puting Technology, Chinese Academy of Sciences; University of Chinese Acad
 emy of Sciences)\n---------------------\nStyle-NeRF2NeRF: 3D Style Transfe
 r from Style-Aligned Multi-View Images\n\nWe propose a simple yet effectiv
 e pipeline for stylizing a 3D scene, harnessing the power of 2D image diff
 usion models. Given a NeRF model reconstructed from a set of multi-view im
 ages, we perform 3D style transfer by refining the source NeRF model using
  stylized images generated by a style-aligned ...\n\n\nHaruo Fujiwara (Uni
 versity of Tokyo) and Yusuke Mukuta and Tatsuya Harada (University of Toky
 o, RIKEN AIP)\n---------------------\nNU-NeRF: Neural Reconstruction of Ne
 sted Transparent Objects with Uncontrolled Capture Environment\n\nThe reco
 nstruction of transparent objects is a challenging problem due to the high
 ly noncontinuous and rapidly changing surface color caused by refraction. 
 Existing methods rely on special capture devices, dedicated backgrounds, o
 r ground-truth object masks to provide more priors and reduce the ambi...\
 n\n\nJia-Mu Sun (Insititute of Computing Technology Chinese Academy of Sci
 ences, KIRI Innovations); Tong Wu (Institute of Computing Technology, Chin
 ese Academy of Sciences; University of Chinese Academy of Sciences); Ling-
 Qi Yan (University of California Santa Barbara); and Lin Gao (Institute of
  Computing Technology, Chinese Academy of Sciences; University of Chinese 
 Academy of Sciences)\n\nRegistration Category: Full Access, Full Access Su
 pporter\n\nLanguage Format: English Language\n\nSession Chair: Maria Larss
 on (The University of Tokyo)
END:VEVENT
END:VCALENDAR