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:20251218T030657Z
LOCATION:Meeting Room S421\, Level 4
DTSTART;TZID=Asia/Hong_Kong:20251216T152200
DTEND;TZID=Asia/Hong_Kong:20251216T153300
UID:siggraphasia_SIGGRAPH Asia 2025_sess124_papers_1687@linklings.com
SUMMARY:Prior-Enhanced Gaussian Splatting for Dynamic Scene Reconstruction
  from Casual Video
DESCRIPTION:Meng-Li Shih (University of Washington); Ying-Huan Chen and Yu
 -Lun Liu (National Yang Ming Chiao Tung University); and Brian Curless (Un
 iversity of Washington, Google Inc.)\n\nWe introduce a fully automatic pip
 eline for dynamic scene reconstruction from casually captured monocular RG
 B videos. Rather than designing a new scene representation, we enhance the
  priors that drive Dynamic Gaussian Splatting. Video segmentation combined
  with epipolar-error maps yields object-level masks that closely follow th
 in structures; these masks (i) guide an object-depth loss that sharpens th
 e consistent video depth, and (ii) support skeleton-based sampling plus ma
 sk-guided re-identification to produce reliable, comprehensive 2-D tracks.
  Two additional objectives embed the refined priors in the reconstruction 
 stage: a virtual-view depth loss removes floaters, and a scaffold-projecti
 on loss ties motion nodes to the tracks, preserving fine geometry and cohe
 rent motion. The resulting system surpasses previous monocular dynamic sce
 ne reconstruction methods and delivers visibly superior renderings.\n\nReg
 istration Category: Full Access, Full Access Supporter\n\nSession Chair: Y
 an-Pei Cao (VAST)\n\n
END:VEVENT
END:VCALENDAR