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:20240214T070246Z
LOCATION:Meeting Room C4.8\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231214T095000
DTEND;TZID=Australia/Melbourne:20231214T100500
UID:siggraphasia_SIGGRAPH Asia 2023_sess148_papers_158@linklings.com
SUMMARY:EXIM: A Hybrid Explicit-Implicit Representation for Text-Guided 3D
  Shape Generation
DESCRIPTION:Technical Papers, TOG\n\nZhengzhe Liu, Jingyu Hu, and Ka-Hei H
 ui (The Chinese University of Hong Kong); Xiaojuan Qi (The University of H
 ong Kong); Daniel Cohen-Or (Tel-Aviv University); and Chi-Wing Fu (The Chi
 nese University of Hong Kong)\n\nThis paper presents a new text-guided tec
 hnique for generating 3D shapes. The technique leverages a hybrid 3D shape
  representation, combining the strengths of explicit and implicit represen
 tations. Specifically, the explicit stage controls the generated topology 
 of the 3D shape and allows local manipulations, while the implicit stage r
 efines the shape and paints it with plausible colors. Also, the hybrid app
 roach separates shape and color, ensuring shape-color consistency. Unlike 
 existing state-of-the-art methods, our technique achieves high-fidelity sh
 ape generation from natural-language descriptions without the need for tim
 e-consuming per-shape optimization or reliance on human-annotated texts du
 ring training or test-time optimization. Furthermore, we demonstrate the e
 xtension of our approach to generate indoor scenes with consistent styles 
 using text-induced 3D shapes. Through extensive experiments, we demonstrat
 e the compelling quality of our results and the high coherency of our gene
 rated shapes with the input texts, surpassing the performance of existing 
 methods by a significant margin.\n\nRegistration Category: Full Access\n\n
 Session Chair: Lin Lu (Shandong University)
URL:https://asia.siggraph.org/2023/full-program?id=papers_158&sess=sess148
END:VEVENT
END:VCALENDAR