BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Seoul
X-LIC-LOCATION:Asia/Seoul
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:KST
DTSTART:18871231T000000
DTSTART:19881009T020000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230103T035346Z
LOCATION:Room 325-AB\, Level 3\, West Wing
DTSTART;TZID=Asia/Seoul:20221206T153000
DTEND;TZID=Asia/Seoul:20221206T170000
UID:siggraphasia_SIGGRAPH Asia 2022_sess157@linklings.com
SUMMARY:Image Generation
DESCRIPTION:Technical Communications, Technical Papers\n\nThe presentation
 s will be followed by a 30-min Interactive Discussion Session at Room 325-
 CD.\n\nThe Technical Papers program is the premier international forum for
  disseminating new scholarly work in computer graphics and interactive tec
 hniques. Technical Papers are published as a special issue of ACM Transact
 ions on Graphics. In addition to papers selected by the SIGGRAPH Asia 2022
  Technical Papers Jury, the conference presents papers that have been publ
 ished in ACM Transactions on Graphics during the past year. Accepted paper
 s adhere to the highest scientific standards.\n\nThe Technical Communicati
 ons program is a premier forum for presenting the latest developments and 
 research still in progress. Leading international experts in academia and 
 industry present work that showcase actual implementations of research ide
 as, works at the crossroads of computer graphics with computer vision, mac
 hine learning, HCI, VR, CAD, visualization, and many others.\n\nText2Light
 : Zero-shot Text-driven HDR Panorama Generation\n\nChen, Wang, Liu\n\nHigh
 -quality HDRIs (High Dynamic Range Images), typically HDR panoramas, are o
 ne of the most popular ways to create photorealistic lighting and 360-degr
 ee reflections of 3D scenes in graphics. Given the difficulty of capturing
  HDRIs, a versatile and controllable generative model is highly desired, w
 ...\n\n---------------------\nOVERPAINT: Automatic Multi-Layer Stencil Gen
 eration without Bridges\n\nFukushima, Qi, Shen, Igarashi\n\nWe propose a n
 ovel method to generate a sequence of bridge-free stencil sheets from an i
 nput image. Our method decomposes a given image into color layers, and con
 structs level maps.\n\n---------------------\nMake Your Own Sprites: Alias
 ing-Aware and Cell-Controllable Pixelization\n\nWu, Chai, Zhao, Deng, Liu.
 ..\n\nPixel art is a unique art style with the appearance of low resolutio
 n images. In this paper, we propose a data-driven pixelization method that
  can produce sharp and crisp cell effects with controllable cell size. Our
  approach overcomes the limitation of existing learning-based methods in c
 ell size c...\n\n---------------------\nDr.3D: Adapting 3D GANs to Artisti
 c Drawings\n\nJin, Ryu, Kim, Baek, Cho\n\nWhile 3D GANs have recently demo
 nstrated the high-quality synthesis of multi-view consistent images and 3D
  shapes, they are mainly restricted to photo-realistic human portraits. Th
 is paper aims to extend 3D GANs to a different, but meaningful visual form
 : artistic portrait drawings. However, extendi...\n\n---------------------
 \nPopStage: The Generation of Stage Cross-Editing Video based on Spatio-Te
 mporal Matching\n\nLee, Yoo, Cho, Kim, Im...\n\nStageMix is a mixed video 
 that is created by concatenating the segments from various performance vid
 eos of an identical song in a visually smooth manner by matching the main 
 subject's silhouette presented in the frame. We introduce PopStage, which 
 allows users to generate a StageMix automatically. P...\n\n---------------
 ------\nSprite-from-Sprite: Cartoon Animation Decomposition with Self-supe
 rvised Sprite Estimation\n\nZhang, Wong, Liu\n\nWe present an approach to 
 decompose cartoon animation videos into a set of ``sprites'' --- the basic
  units of digital cartoons that depict the contents and transforms of each
  animated objects. The sprites in real-world cartoons are unique: artists 
 may draw arbitrary sprite animations for expressiven...\n\n---------------
 ------\nDynaGAN: Dynamic Few-shot Adaptation of GANs to Multiple Domains\n
 \nKim, Kang, Kim, Baek, Cho\n\nFew-shot domain adaptation to multiple doma
 ins aims to learn a complex image distribution across multiple domains fro
 m a few training images. A naive solution here is to train a separate mode
 l for each domain using few-shot domain adaptation methods. Unfortunately,
  this approach mandates linearly-sc...\n\n\nRegistration Category: FULL AC
 CESS, ON-DEMAND ACCESS\n\nLanguage: ENGLISH\n\nFormat: IN-PERSON, ON-DEMAN
 D
END:VEVENT
END:VCALENDAR