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 B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241206T153100
DTEND;TZID=Asia/Tokyo:20241206T154300
UID:siggraphasia_SIGGRAPH Asia 2024_sess149_papers_936@linklings.com
SUMMARY:Procedural Material Generation with Reinforcement Learning
DESCRIPTION:Technical Papers\n\nBeichen Li (MIT CSAIL, Adobe Research); Yi
 wei Hu, Paul Guerrero, and Milos Hasan (Adobe Research); Liang Shi (MIT CS
 AIL); Valentin Deschaintre (Adobe Research); and Wojciech Matusik (MIT CSA
 IL)\n\nModern 3D content creation heavily relies on procedural assets. In 
 particular, procedural materials are ubiquitous in the industry, but their
  manipulation remains challenging. Previous work conditionally generates p
 rocedural graphs that match a given input image. However, the parameter ge
 neration step limits how accurately the generated graph matches the input 
 image, due to a reliance on supervision with scarcely available procedural
  data. We propose to improve parameter prediction accuracy for image-condi
 tioned procedural material generation by leveraging reinforcement learning
  (RL) and present the first RL approach for procedural materials. RL circu
 mvents the limited availability of procedural data, the domain gap between
  real and synthetic materials, and the need for end-to-end differentiable 
 loss functions. Given a target image, we retrieve a procedural material an
 d use an RL-trained transformer model to predict a set of parameters that 
 reconstruct the target image as closely as possible. We show that using RL
  significantly improves parameter prediction to match a given target image
  compared to supervised methods on both synthetic and real target images.\
 n\nRegistration Category: Full Access, Full Access Supporter\n\nLanguage F
 ormat: English Language\n\nSession Chair: Valentin Deschaintre (Adobe Rese
 arch)
URL:https://asia.siggraph.org/2024/program/?id=papers_936&sess=sess149
END:VEVENT
END:VCALENDAR