BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Garment Draping over the Human Body
DTSTART:20220701T093000
DTEND:20220701T113000
DTSTAMP:20260509T054507Z
UID:d6f3f91e5484cf6b604dc355323b5138ed2756b3d7338a91f71585fc
CATEGORIES:Conferences - Seminars
DESCRIPTION:Ren LI\nEDIC candidacy exam\nExam president: Prof. Sabine Süs
 strunk\nThesis advisor: Prof. Pascal Fua\nCo-examiner: Prof. Ronan Boulic\
 n\nAbstract\nWe consider the problem of draping garment over posed human b
 ody. Traditionally\, the physics-based simulator is used to model garment 
 deformation due to the high fidelity of simulation results. However\, its 
 computation cost is notoriously heavy\, which hinders its deployment in re
 al-world applications. To meet the real-time or near-real time requirement
 \, recent works propose learning-based methods to learn how to deform garm
 ent in supervised or self-supervised fashions. Although these methods are 
 able to produce plausible dynamics and details with fast speed\, we observ
 e that none of them is fully differentiable and scalable to garment with a
 ny topology. This observation leads to our proposed method that is end-to-
 end differentiable\, capable to capture fine details of garment in arbitra
 ry topology\, and even supports topology changing according to external si
 gnals\, e.g.\, 3D scans\, 2D segmentation or sketches of garment.\n\nBackg
 round papers\n\n	 Narain et al. Adaptive Anisotropic Remeshing for Cloth
  Simulation - https://dl.acm.org/doi/pdf/10.1145/2366145.2366171\n	Sant
 esteban et al. SNUG: Self-Supervised Neural Dynamic Garments - http://m
 slab.es/projects/SNUG/contents/santesteban_CVPR2022.pdf\n	Corona et al. S
 MPLicit: Topology-aware Generative Model for Clothed People - https://op
 enaccess.thecvf.com/content/CVPR2021/papers/Corona_SMPLicit_Topology-Aware
 _Generative_Model_for_Clothed_People_CVPR_2021_paper.pdf\n
LOCATION:BC 333 https://plan.epfl.ch/?room==BC%20333
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR