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:20250110T023312Z
LOCATION:Hall B5 (1)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241205T172800
DTEND;TZID=Asia/Tokyo:20241205T174000
UID:siggraphasia_SIGGRAPH Asia 2024_sess136_papers_616@linklings.com
SUMMARY:MagicClay: Sculpting Meshes With Generative Neural Fields
DESCRIPTION:Technical Papers\n\nAmir Barda (Tel Aviv University), Vladimir
  Kim (Adobe Research), Noam Aigerman (Université de Montréal), Amit Haim B
 ermano (Tel Aviv University), and Thibault Groueix (Adobe Research)\n\nThe
  recent developments in neural fields have brought phenomenal capabilities
  to the field of shape generation, but they lack crucial properties, such 
 as incremental control --- a fundamental requirement for artistic work. Tr
 iangular meshes, on the other hand, are the representation of choice for m
 ost geometry-related tasks, offering efficiency and intuitive control, but
  do not lend themselves to neural optimization. \nTo support downstream ta
 sks, previous art typically proposes a two-step approach, where first, a s
 hape is generated using neural fields, and then a mesh is extracted for fu
 rther processing. Instead, in this paper, we introduce a hybrid approach t
 hat maintains both a mesh and a Signed Distance Field (SDF) representation
 s consistently. Using this representation, we introduce MagicClay --- an a
 rtist friendly tool for sculpting regions of a mesh according to textual p
 rompts while keeping other regions untouched.\nOur framework carefully and
  efficiently balances consistency between the representations and regulari
 zations in every step of the shape optimization. Relying on the mesh repre
 sentation, we show how to render the SDF at higher resolutions and faster.
  In addition, we employ recent work in differentiable mesh reconstruction 
 to adaptively allocate triangles in the mesh where required, as indicated 
 by the SDF.\nUsing an implemented prototype, we demonstrate superior gener
 ated geometry compared to the state-of-the-art, and novel consistent contr
 ol, allowing sequential prompt-based edits to the same mesh for the first 
 time. \nWe will release the code upon acceptance.\n\nRegistration Category
 : Full Access, Full Access Supporter\n\nLanguage Format: English Language\
 n\nSession Chair: Manolis Savva (Simon Fraser University)
URL:https://asia.siggraph.org/2024/program/?id=papers_616&sess=sess136
END:VEVENT
END:VCALENDAR