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 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241204T105600
DTEND;TZID=Asia/Tokyo:20241204T110800
UID:siggraphasia_SIGGRAPH Asia 2024_sess113_papers_500@linklings.com
SUMMARY:Pano2Room: Novel View Synthesis from a Single Indoor Panorama
DESCRIPTION:Technical Papers\n\nGuo Pu, Yiming Zhao, and Zhouhui Lian (Wan
 gxuan Institute of Computer Technology, Peking University)\n\nRecent singl
 e-view 3D AIGC methods have made significant advancements by leveraging kn
 owledge distilled from extensive 3D object datasets. However, challenges p
 ersist in the synthesis of 3D scenes from a single view, primarily due to 
 the complexity of real-world environments and the limited availability of 
 high-quality prior resources.\nIn this paper, we introduce a novel approac
 h called Pano2room, designed to automatically reconstruct high-quality 3D 
 indoor scenes from a single panoramic image. These panoramic images can be
  easily generated using a panoramic RGBD inpainter from captures at a sing
 le location with any camera.\nThe key idea is to initially construct a pre
 liminary mesh from the input panorama, and iteratively refine this mesh us
 ing a panoramic RGBD inpainter while collecting photo-realistic 3D-consist
 ent pseudo novel views. Finally the refined mesh is converted into a 3D Ga
 ussian Splatting field and trained with the collected pseudo novel views. 
 This pipeline enables the reconstruction of real-world 3D scenes, even in 
 the presence of large occlusions, and facilitates the synthesis of photo-r
 ealistic novel views with detailed geometry.\nExtensive qualitative and qu
 antitative experiments have been conducted to validate the superiority of 
 our method in single-panorama indoor novel synthesis compared to the state
  of the art. Our code and data will be available at https://github.com/***
 .\n\nRegistration Category: Full Access, Full Access Supporter\n\nLanguage
  Format: English Language\n\nSession Chair: Forrester Cole (Google)
URL:https://asia.siggraph.org/2024/program/?id=papers_500&sess=sess113
END:VEVENT
END:VCALENDAR