BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260114T163648Z
LOCATION:Meeting Room C4.11\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231214T103000
DTEND;TZID=Australia/Melbourne:20231214T104000
UID:siggraphasia_SIGGRAPH Asia 2023_sess129_papers_586@linklings.com
SUMMARY:ShaDDR: Interactive Example-Based Geometry and Texture Generation 
 via 3D Shape Detailization and Differentiable Rendering
DESCRIPTION:Qimin Chen, Zhiqin Chen, Hang Zhou, and Hao Zhang (Simon Frase
 r University)\n\nWe present ShaDDR, an example-based deep generative neura
 l network which produces a high-resolution textured 3D shape through geome
 try detailization and conditional texture generation applied to an input c
 oarse voxel shape. Trained on a small set of detailed and textured exempla
 r shapes, our method learns to detailize the geometry via multi-resolution
  voxel upsampling and generate textures on voxel surfaces via differentiab
 le rendering against exemplar texture images from a few views. The generat
 ion is real-time, taking less than 1 second to produce a 3D model with vox
 el resolutions up to 512^3. The generated shape preserves the overall stru
 cture of the input coarse voxel model, while the style of the generated ge
 ometric details and textures can be manipulated through learned latent cod
 es. In the experiments, we show that our method can generate higher-resolu
 tion shapes with plausible and improved geometric details and clean textur
 es compared to prior works. Furthermore, we showcase the ability of our me
 thod to learn geometric details and textures from shapes reconstructed fro
 m real-world photos. In addition, we have developed an interactive modelin
 g application to demonstrate the generalizability of our method to various
  user inputs and the controllability it offers, allowing users to interact
 ively sculpt a coarse voxel shape to define the overall structure of the d
 etailized 3D shape.\n\nRegistration Category: Full Access\n\nSession Chair
 : Marc Stamminger (Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU)
 )\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_586&sess=sess129
END:VEVENT
END:VCALENDAR
