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:20260817T171530Z
LOCATION:Hall B5 (1)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241206T131400
DTEND;TZID=Asia/Tokyo:20241206T132800
UID:siggraphasia_SIGGRAPH Asia 2024_sess145_papers_544@linklings.com
SUMMARY:Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction
  in Unbounded Scenes
DESCRIPTION:Zehao Yu (University of Tübingen, Tübingen AI Center); Torsten
  Sattler (Czech Technical University in Prague); and Andreas Geiger (Unive
 rsity of Tübingen, Tübingen AI Center)\n\nRecently, 3D Gaussian Splatting 
 (3DGS) has demonstrated impressive novel view synthesis results, while all
 owing the rendering of high-resolution images in real-time. However, lever
 aging 3D Gaussians for surface reconstruction poses significant challenges
  due to the explicit and disconnected nature of 3D Gaussians. In this work
 , we present Gaussian Opacity Fields (GOF), a novel approach for efficient
 , high-quality, and adaptive surface reconstruction in unbounded scenes. O
 ur GOF is derived from ray-tracing-based volume rendering of 3D Gaussians,
  enabling direct geometry extraction from 3D Gaussians by identifying its 
 levelset, without resorting to Poisson reconstruction or TSDF fusion as in
  previous work. We approximate the surface normal of Gaussians as the norm
 al of the ray-Gaussian intersection plane, enabling the application of reg
 ularization that significantly enhances geometry. Furthermore, we develop 
 an efficient geometry extraction method utilizing Marching Tetrahedra, whe
 re the tetrahedral grids are induced from 3D Gaussians and thus adapt to t
 he scene's complexity. Our evaluations reveal that GOF surpasses existing 
 3DGS-based methods in surface reconstruction and novel view synthesis. Fur
 ther, it compares favorably to or even outperforms, neural implicit method
 s in both quality and speed.\n\nRegistration Category: Full Access, Full A
 ccess Supporter\n\nLanguage Format: English Language\n\nSession Chair: Hao
  (Richard) Zhang (Simon Fraser University, Augmenta)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_544&sess=sess145
END:VEVENT
END:VCALENDAR