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:20231213T140000
DTEND;TZID=Australia/Melbourne:20231213T150500
UID:siggraphasia_SIGGRAPH Asia 2023_sess128@linklings.com
SUMMARY:How To Deal With NERF?
DESCRIPTION:Technical Papers\n\nSimpleNeRF: Regularizing Sparse Input Neur
 al Radiance Fields with Simpler Solutions\n\nNeural Radiance Fields (NeRF)
  show impressive performance for the photo-realistic free-view rendering o
 f scenes. However, NeRFs require dense sampling of images in the given sce
 ne, and their performance degrades significantly when only a sparse set of
  views are available. Researchers have found that...\n\n\nNagabhushan Somr
 aj, Adithyan Karanayil, and Rajiv Soundararajan (Indian Institute of Scien
 ce)\n---------------------\nGANeRF: Leveraging Discriminators to Optimize 
 Neural Radiance Fields\n\nNeural Radiance Fields (NeRF) have shown impress
 ive novel view synthesis results; nonetheless, even thorough recordings yi
 eld imperfections in reconstructions, for instance due to poorly observed 
 areas or minor lighting changes.\nOur goal is to mitigate these imperfecti
 ons from various sources with a...\n\n\nBarbara Roessle and Norman Müller 
 (Technical University of Munich); Lorenzo Porzi, Samuel Rota Bulò, and Pet
 er Kontschieder (Meta Reality Labs); and Matthias Niessner (Technical Univ
 ersity of Munich)\n---------------------\nCamP: Camera Preconditioning for
  Neural Radiance Fields\n\nNeural Radiance Fields (NeRF) can be optimized 
 to obtain high-fidelity 3D scene reconstructions of objects and large-scal
 e scenes. However, NeRFs require accurate camera parameters as input --- i
 naccurate camera parameters result in blurry renderings. Extrinsic and int
 rinsic camera parameters are us...\n\n\nKeunhong Park, Phillip Henzler, Be
 n Mildenhall, Jonathan T. Barron, and Ricardo Martin-Brualla (Google Resea
 rch)\n---------------------\nNeural Field Convolutions by Repeated Differe
 ntiation\n\nNeural fields are evolving towards a general-purpose continuou
 s representation for visual computing. Yet, despite their numerous appeali
 ng properties, they are hardly amenable to signal processing. As a remedy,
  we present a method to perform general continuous convolutions with gener
 al continuous si...\n\n\nNtumba Elie Nsampi, Adarsh Djeacoumar, and Hans-P
 eter Seidel (Max-Planck-Institut für Informatik); Tobias Ritschel (Univers
 ity College London (UCL)); and Thomas Leimkühler (Max-Planck-Institut für 
 Informatik)\n---------------------\nDreamEditor: Text-Driven 3D Scene Edit
 ing with Neural Fields\n\nNeural fields have achieved impressive advanceme
 nts in view synthesis and scene reconstruction. However, editing these neu
 ral fields remains challenging due to the implicit encoding of geometry an
 d texture information. In this paper, we propose DreamEditor, a novel fram
 ework that enables users to pe...\n\n\nJingyu Zhuang (Sun Yat-sen Universi
 ty); Chen Wang (University of Pennsylvania, Tsinghua University); Liang Li
 n (Sun Yat-sen University); Lingjie Liu (University of Pennsylvania); and 
 Guanbin Li (Sun Yat-sen University)\n\nRegistration Category: Full Access\
 n\nSession Chair: Jianfei Cai (Monash University)
END:VEVENT
END:VCALENDAR