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:20240214T070311Z
LOCATION:Meeting Room C4.11\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231213T164000
DTEND;TZID=Australia/Melbourne:20231213T173100
UID:siggraphasia_SIGGRAPH Asia 2023_sess153@linklings.com
SUMMARY:Anything Can be Neural
DESCRIPTION:Technical Communications, Technical Papers\n\nLayerDiffusion: 
 Layered Controlled Image Editing with Diffusion Models\n\nWe propose Layer
 Diffusion, a semantic-based controlled image editing method. Our method en
 ables non-rigid editing and attribute modification of specific subjects wh
 ile preserving unique characteristics and integrating them into new backgr
 ounds.\n\n\nPengzhi Li, Qinxuan Huang, Yikang Ding, and Zhiheng Li (Tsingh
 ua University)\n---------------------\nVET: Visual Error Tomography for Po
 int Cloud Completion and High-Quality Neural Rendering\n\nIn the last few 
 years, deep neural networks opened the doors for big advances in novel vie
 w synthesis. Many of these approaches are based on a (coarse) proxy geomet
 ry obtained by structure from motion algorithms. Small deficiencies in thi
 s proxy can be fixed by neural rendering, but larger holes or ...\n\n\nLin
 us Franke, Darius Rückert, and Laura Fink (Friedrich-Alexander Universität
  Erlangen-Nürnberg); Matthias Innmann (NavVis GmbH); and Marc Stamminger (
 Friedrich-Alexander Universität Erlangen-Nürnberg)\n---------------------\
 nLiveNVS: Neural View Synthesis on Live RGB-D Streams\n\nExisting real-tim
 e RGB-D reconstruction approaches, like Kinect Fusion, lack real-time phot
 o-realistic visualization. This is due to noisy, oversmoothed or incomplet
 e geometry and blurry textures which are fused from imperfect depth maps a
 nd camera poses. Recent neural rendering methods can overcome...\n\n\nLaur
 a Fink (Friedrich-Alexander-Universität Erlangen-Nürnberg, Fraunhofer IIS)
 ; Darius Rückert and Linus Franke (Friedrich-Alexander-Universität Erlange
 n-Nürnberg); Joachim Keinert (Fraunhofer IIS); and Marc Stamminger (Friedr
 ich-Alexander-Universität Erlangen-Nürnberg)\n---------------------\nAeria
 l Diffusion: Text Guided Ground-to-Aerial View Synthesis from a Single Ima
 ge using Diffusion Models\n\nAerial Diffusion is one of the first approach
 es towards unsupervised ground-to-aerial view synthesis using a single ima
 ge and the corresponding text description.\n\n\nDivya Kothandaraman, Tiany
 i Zhou, Ming Lin, and Dinesh Manocha (University of Maryland College Park)
 \n---------------------\nA Neural Implicit Representation for the Image St
 ack: Depth, All in Focus, and High Dynamic Range\n\nIn everyday photograph
 y, physical limitations of camera sensors and lenses frequently lead to a 
 variety of degradations in captured images such as saturation or defocus b
 lur. A common approach to overcome these limitations is to resort to image
  stack fusion, which involves capturing multiple images ...\n\n\nChao Wang
  (Max-Planck-Institut für Informatik); Ana Serrano (Universidad de Zaragoz
 a); and Xingang Pan, Bin Chen, Hans-Peter Seidel, Karol Myszkowski, Christ
 ian Theobalt, Krzysztof Wolski, and Thomas Leimkühler (Max-Planck-Institut
  für Informatik)\n\nRegistration Category: Full Access\n\nSession Chair: J
 onah Brucker-Cohen (Lehman College / CUNY, New Inc.)
END:VEVENT
END:VCALENDAR