BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
X-LIC-LOCATION:Asia/Hong_Kong
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:HKT
DTSTART:19911015T033000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251218T030331Z
LOCATION:Meeting Room S423+S424\, Level 4
DTSTART;TZID=Asia/Hong_Kong:20251217T104000
DTEND;TZID=Asia/Hong_Kong:20251217T114500
UID:siggraphasia_SIGGRAPH Asia 2025_sess135@linklings.com
SUMMARY:Generative Scenes & Panoramas
DESCRIPTION:The Technical Papers program is the heartbeat of SIGGRAPH Asia
 , spotlighting world-class scholarly research at the forefront of computer
  graphics and interactive techniques. For decades, it has been the definit
 ive venue where bold ideas take root, foundational concepts are reimagined
 , and the future of visual computing is shaped.\n\nThis year, we explore n
 ew intersections of algorithms and artistry, automation and authorship, to
 ols and imagination – challenging the very way we design, simulate, visual
 ize, and interact with digital worlds.\n\nPanoDreamer: Optimization-Based 
 Single Image to 360 3D Scene With Diffusion\n\nIn this paper, we present P
 anoDreamer, a novel method for producing a coherent 360° 3D scene from a s
 ingle input image. Unlike existing methods that generate the scene sequent
 ially, we frame the problem as single-image panorama and depth estimation.
  Once the coherent panoramic image and its correspo...\n\n\nAvinash Paliwa
 l (Texas A&M University, Morphic Inc); Xilong Zhou (Max Planck Institute f
 or Informatics); Andrii Tsarov (Leia Inc.); and Nima Kalantari (Texas A&M 
 University)\n---------------------\nGenerating 360° Video is What You Need
  For a 3D Scene\n\nGenerating 3D scenes is still a challenging task due to
  the lack of readily available scene data. Most existing methods only prod
 uce partial scenes and provide limited navigational freedom. We introduce 
 a practical and scalable solution that uses 360° video as an intermediate 
 scene representation, c...\n\n\nZhaoyang Zhang (Yale University, Adobe Res
 earch); Yannick Hold-Geoffroy and Miloš Hašan (Adobe Research); Ziwen Chen
  (Oregon State University); Fujun Luan (Adobe Research); Julie Dorsey (Yal
 e University); and Yiwei Hu (Adobe Research)\n---------------------\nVideo
 From3D: 3D Scene Video Generation via Complementary Image and Video Diffus
 ion Models\n\nIn this paper, we propose VideoFrom3D, a novel framework for
  synthesizing high-quality 3D scene videos from coarse geometry, a camera 
 trajectory, and a reference image. Our approach streamlines the 3D graphic
  design workflow, enabling flexible design exploration and rapid productio
 n of deliverables....\n\n\nGeonung Kim, Janghyeok Han, and Sunghyun Cho (P
 OSTECH)\n---------------------\nWorldExplorer: Towards Generating Fully Na
 vigable 3D Scenes\n\nGenerating 3D worlds from text is a highly anticipate
 d goal in computer vision. Existing works are limited by the degree of exp
 loration they allow inside of a scene, i.e., produce streched-out and nois
 y artifacts when moving beyond central or panoramic perspectives. To this 
 end, we propose WorldExpl...\n\n\nManuel-Andreas Schneider, Lukas Höllein,
  and Matthias Niessner (Technical University of Munich)\n-----------------
 ----\nSS4D: Native 4D Generative Model via Structured Spacetime Latents\n\
 nWe present SS4D, a native 4D generative model that synthesizes dynamic 3D
  objects directly from monocular video. Unlike prior approaches that const
 ruct 4D representations by optimizing over 3D or video generative models, 
 we train a generator directly on 4D data, achieving high fidelity, tempora
 l coh...\n\n\nZhibing Li (The Chinese University of Hong Kong); Mengchen Z
 hang (Zhejiang University, Shanghai Artificial Intelligence Laboratory); T
 ong Wu (Stanford University); Jing Tan (Chinese University of Hong Kong); 
 Jiaqi Wang (Shanghai AI Laboratory); and Dahua Lin (The Chinese University
  of Hong Kong)\n---------------------\nVoyager: Long-Range and World-Consi
 stent Video Diffusion for Explorable 3D Scene Generation\n\nReal-world app
 lications like video gaming and virtual reality often demand the ability t
 o model 3D scenes that users can explore along custom camera trajectories.
  While significant progress has been made in generating 3D objects from te
 xt or images, creating long-range, 3D-consistent, explorable 3D ...\n\n\nT
 ianyu Huang (Harbin Institute of Technology, City University of Hong Kong)
 ; Wangguandong Zheng and Tengfei Wang (Tencent); Yuhao Liu (Tencent, City 
 University of Hong Kong); Zhenwei Wang, Junta Wu, and Jie Jiang (Tencent);
  Hui Li (Harbin Institute of Technology); Rynson Lau (City University of H
 ong Kong); Wangmeng Zuo (Harbin Institute of Technology); and Chunchao Guo
  (Tencent)\n\nRegistration Category: Full Access, Full Access Supporter\n\
 nSession Chair: Or Patashnik (Tel Aviv University, Snap Research)
END:VEVENT
END:VCALENDAR