BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250522T212947Z
LOCATION:Mile High 4
DTSTART;TZID=America/Denver:20240801T154500
DTEND;TZID=America/Denver:20240801T171500
UID:siggraph_SIGGRAPH 2024_sess141@linklings.com
SUMMARY:Art, illusion, Fabrication
DESCRIPTION:Cross-image Attention for Zero-shot Appearance Transfer\n\nOur
  zero-shot appearance transfer approach leverages the semantic understandi
 ng of text-to-image models to transfer visual appearance across semantical
 ly similar objects. Using our cross-image attention, we establish semantic
  correspondences between two images, combining one image's structure with 
 a...\n\n\nYuval Alaluf, Daniel Garibi, Or Patashnik, Hadar Averbuch-Elor, 
 and Daniel Cohen-Or (Tel Aviv University)\n---------------------\nFabricab
 le 3D Wire Art\n\nWe computationally create fabricable 3D wire sculptures 
 from various input modalities, including 3D models, images, and texts. Our
  curve design algorithm automatically abstracts the various inputs using a
  pre-trained, vision-language model and ensures fabricability using geomet
 rical constraints. 3D-...\n\n\nKenji Tojo (University of Tokyo); Ariel Sha
 mir (Reichman University); Bernd Bickel (Institute of Science and Technolo
 gy Austria (ISTA), ETH Zürich); and Nobuyuki Umetani (University of Tokyo)
 \n---------------------\nArt, illusion, Fabrication - Interactive Discussi
 on\n\nAfter the summary presentations, attendees will participate in an in
 teractive discussion. Distributed around the room will be a series of post
 er boards for authors to gather around with the audience. Authors are invi
 ted to bring any material related to their paper that could instigate furt
 her conver...\n\n---------------------\nCreating LEGO Figurines From Singl
 e Images\n\nThis paper introduces a three-stage computational pipeline for
  creating personalized LEGO figurines from portrait photos: CLIP-guided te
 mplate-model creation, decal extraction and generation, and physical const
 ruction. The resulting figurines not only look like the inputs in the port
 rait photos with...\n\n\nJiahao Ge, Mingjun Zhou, and Wenrui Bao (The Chin
 ese University of Hong Kong); Hao Xu (Qianzhi Technology Inc); and Chi-Win
 g Fu (The Chinese University of Hong Kong)\n---------------------\nGenerat
 ive Escher Meshes\n\nThis work achieves a text-guided automatic technique 
 for generating visually pleasing 2D tilings similar to the works of M.C. E
 scher. The method relies on a new parameterization of the space of valid t
 iles using Orbifold Tutte Embeddings and spaces of Laplacians, which enabl
 es simple gradient-based ...\n\n\nNoam Aigerman (University of Montreal) a
 nd Thibault Groueix (Adobe Research)\n---------------------\nComputational
  Illusion Knitting\n\nIllusion-knit fabrics reveal hidden images across vi
 ewing angles. Artist-created knit illusions are tedious to design, limited
  to single-view, and slow to manufacture. We establish constraints over th
 e design space, develop an interactive design system, and originate fabric
 ation techniques for mixed...\n\n\nAmy Zhu, Yuxuan Mei, Benjamin Jones, Za
 chary Tatlock, and Adriana Schulz (University of Washington)\n------------
 ---------\nDiffusion Illusions: Hiding Images in Plain Sight\n\nDiffusion 
 Illusions: Hiding Images In Plain Sight — a novel pipeline for computation
 ally generating special images that produce secret new images when physica
 lly arranged in the real world. Training-free, it adapts a frozen text-to-
 image diffusion model to optimize these images using score-dis...\n\n\nRya
 n Burgert, Xiang Li, Abe Leite, and Kanchana Ranasinghe (Stony Brook Unive
 rsity) and Michael Ryoo (Stony Brook University, Google)\n\nInterest Area:
  Research & Education\n\nRegistration Category: Full Conference, Full Conf
 erence Supporter, Virtual Access, Exhibitor Full Conference, Thursday\n\nS
 ession Chair: Aaron Hertzmann (Adobe)
END:VEVENT
END:VCALENDAR