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:20260114T163642Z
LOCATION:Meeting Room C4.9+C4.10\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231212T170000
DTEND;TZID=Australia/Melbourne:20231212T175000
UID:siggraphasia_SIGGRAPH Asia 2023_sess162@linklings.com
SUMMARY:View Synthesis
DESCRIPTION:Repurposing Diffusion Inpainters for Novel View Synthesis\n\nI
 n this paper, we present a method for generating consistent novel views fr
 om a single source image. Our approach focuses on maximizing the reuse of 
 visible pixels from the source view. To achieve this, we use a monocular d
 epth estimator that transfers visible pixels from the source view to the t
 arg...\n\n\nYash Kant (University of Toronto, Snap Inc.); Aliaksandr Siaro
 hin, Michael Vasilkovsky, Riza Alp Guler, Jian Ren, and Sergey Tulyakov (S
 nap Inc.); and Igor Gilitschenski (University of Toronto)\n---------------
 ------\nSinMPI: Novel View Synthesis from a Single Image with Expanded Mul
 tiplane Images\n\nSingle-image novel view synthesis is a challenging and o
 ngoing problem that aims to generate an infinite number of consistent view
 s from a single input image. Although significant efforts have been made t
 o advance the quality of generated novel views, less attention has been pa
 id to the expansion of...\n\n\nGuo Pu, Peng-Shuai Wang, and Zhouhui Lian (
 Wangxuan Institute of Computer Technology, Peking University)\n-----------
 ----------\nHigh-Fidelity and Real-Time Novel View Synthesis for Dynamic S
 cenes\n\nThis paper aims to tackle the challenge of dynamic view synthesis
  from multi-view videos. The key observation is that while previous grid-b
 ased methods offer consistent rendering, they fall short in capturing appe
 arance details on a complex dynamic scene, a domain where multi-view image
 -based method...\n\n\nHaotong Lin (State Key Laboratory of CAD & CG, Zheji
 ang University); Sida Peng (Zhejiang University); and Zhen Xu, Tao Xie, Xi
 ngyi He, Hujun Bao, and Xiaowei Zhou (State Key Laboratory of CAD & CG, Zh
 ejiang University)\n---------------------\nVMesh: Hybrid Volume-Mesh Repre
 sentation for Efficient View Synthesis\n\nWith the emergence of neural rad
 iance fields (NeRFs), view synthesis quality has reached an unprecedented 
 level. Compared to traditional mesh-based assets, this volumetric represen
 tation is more powerful in expressing scene geometry but inevitably suffer
 s from high rendering costs and can hardly be ...\n\n\nYuan-Chen Guo (Tsin
 ghua University, Tencent); Yan-Pei Cao (Tencent); Chen Wang (Tsinghua Univ
 ersity); Yu He (Chinese Academy of Sciences); Ying Shan (Tencent); and Son
 g-Hai Zhang (Tsinghua University)\n---------------------\nInovis: Instant 
 Novel-View Synthesis\n\nNovel-view synthesis is an ill-posed problem in th
 at it requires inference of previously unseen information. Recently, reviv
 ing the traditional field of image-based rendering, neural methods proved 
 particularly suitable for this interpolation/extrapolation task; however, 
 they often require a-priori ...\n\n\nMathias Harrer and Linus Franke (Frie
 drich-Alexander-Universität Erlangen-Nürnberg); Laura Fink (Friedrich-Alex
 ander-Universität Erlangen-Nürnberg, Fraunhofer IIS); and Marc Stamminger 
 and Tim Weyrich (Friedrich-Alexander-Universität Erlangen-Nürnberg)\n\nReg
 istration Category: Full Access\n\nSession Chair: Binh-Son Hua (Trinity Co
 llege Dublin)
END:VEVENT
END:VCALENDAR