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:20251218T030653Z
LOCATION:Meeting Room S423+S424\, Level 4
DTSTART;TZID=Asia/Hong_Kong:20251217T132000
DTEND;TZID=Asia/Hong_Kong:20251217T133100
UID:siggraphasia_SIGGRAPH Asia 2025_sess138_papers_1841@linklings.com
SUMMARY:Detail Enhanced Gaussian Splatting for Large-Scale Volumetric Capt
 ure
DESCRIPTION:Julien Philip, Li Ma, Pascal Clausen, Wenqi Xian, Ahmet Levent
  Taşel, Mingming He, Xueming Yu, David George, Ning Yu, Oliver Pilarski, a
 nd Paul Debevec (Eyeline)\n\nWe present a unique system for large-scale, m
 ulti-performer, high resolution 4D volumetric capture providing realistic 
 free-viewpoint video up to and including 4K resolution facial closeups. To
  achieve this, we employ a novel volumetric capture, reconstruction and re
 ndering pipeline based on Dynamic Gaussian Splatting and Diffusion-based D
 etail Enhancement. We design our pipeline specifically to meet the demands
  of high-end media production. We employ two capture rigs: the Scene Rig, 
 which captures multi-actor performances at a resolution which falls short 
 of 4K production quality, and the Face Rig, which records high-fidelity si
 ngle-actor facial detail to serve as a reference for detail enhancement. W
 e first reconstruct dynamic performances from the Scene Rig using 4D Gauss
 ian Splatting, incorporating new model designs and training strategies to 
 improve reconstruction, dynamic range, and rendering quality. Then to rend
 er high-quality images for facial closeups, we introduce a diffusion-based
  detail enhancement model. This model is fine-tuned with high-fidelity dat
 a from the same actors recorded in the Face Rig. We train on paired data g
 enerated from low- and high-quality Gaussian Splatting (GS) models, using 
 the low-quality input to match the quality of the Scene Rig, with the high
 -quality GS as ground truth. Our results demonstrate the effectiveness of 
 this pipeline in bridging the gap between the scalable performance capture
  of a large-scale rig and the high-resolution standards required for film 
 and media production.\n\nRegistration Category: Full Access, Full Access S
 upporter\n\nSession Chair: Bing Wang (University of Oxford, Hong Kong Poly
 technic University)\n\n
END:VEVENT
END:VCALENDAR