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:20250110T023313Z
LOCATION:Hall B7 (1)\, B Block\, Level 7
DTSTART;TZID=Asia/Tokyo:20241206T095800
DTEND;TZID=Asia/Tokyo:20241206T100900
UID:siggraphasia_SIGGRAPH Asia 2024_sess141_papers_472@linklings.com
SUMMARY:Neural Garment Dynamic Super-Resolution
DESCRIPTION:Technical Papers\n\nMeng Zhang and Jun Li (Nanjing University 
 of Science and Technology)\n\nAchieving efficient, high-fidelity, high-res
 olution garment simulation is challenging due to its computational demands
 . Conversely, low-resolution garment simulation is more accessible and ide
 al for low-budget devices like smartphones. In this paper, we introduce a 
 lightweight, learning-based method for garment dynamic super-resolution, d
 esigned to efficiently enhance high-resolution, high-frequency details in 
 low-resolution garment simulations. Starting with low-resolution garment s
 imulation and underlying body motion, we utilize a mesh-graph-net to compu
 te super-resolution features based on coarse garment dynamics and garment-
 body interactions. These features are then used by a hyper-net to construc
 t an implicit function of detailed wrinkle residuals for each coarse mesh 
 triangle. Considering the influence of coarse garment shapes on detailed w
 rinkle performance, we correct the coarse garment shape and predict detail
 ed wrinkle residuals using these implicit functions. Finally, we generate 
 detailed high-resolution garment geometry by applying the detailed wrinkle
  residuals to the corrected coarse garment. Our method enables roll-out pr
 ediction by iteratively using its predictions as input for subsequent fram
 es, producing fine-grained wrinkle details to enhance the low-resolution s
 imulation. Despite training on a small dataset, our network robustly gener
 alizes to different body shapes, motions, and garment types not present in
  the training data. We demonstrate significant improvements over state-of-
 the-art alternatives, particularly in enhancing the quality of high-freque
 ncy, fine-grained wrinkle details.\n\nRegistration Category: Full Access, 
 Full Access Supporter\n\nLanguage Format: English Language\n\nSession Chai
 r: Sheldon Andrews (École de technologie supérieure (ÉTS))
URL:https://asia.siggraph.org/2024/program/?id=papers_472&sess=sess141
END:VEVENT
END:VCALENDAR