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:20260114T163648Z
LOCATION:Meeting Room C4.11\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231214T140000
DTEND;TZID=Australia/Melbourne:20231214T150000
UID:siggraphasia_SIGGRAPH Asia 2023_sess130@linklings.com
SUMMARY:Reconstruction
DESCRIPTION:MIPS-Fusion: Multi-Implicit-Submaps for Scalable and Robust On
 line Neural RGB-D Reconstruction\n\nWe introduce MIPS-Fusion, a robust and
  scalable online RGB-D reconstruction method based on a novel neural impli
 cit representation -- multi-implicit-submap. Different from existing neura
 l RGB-D reconstruction methods lacking either flexibility with a single ne
 ural map or scalability due to extra sto...\n\n\nYijie Tang (National Univ
 ersity of Defense Technology (NUDT)), Jiazhao Zhang (Peking University), Z
 hinan Yu (National University of Defense Technology (NUDT)), He Wang (Peki
 ng University), and Kai Xu (National University of Defense Technology (NUD
 T))\n---------------------\n360° Reconstruction From a Single Image Using 
 Space Carved Outpainting\n\nWe introduce POP3D, a novel framework that cre
 ates a full $360^\circ$-view 3D model from a single image. POP3D resolves 
 two prominent issues that limit the single-view reconstruction. Firstly, P
 OP3D offers substantial generalizability to arbitrary categories, a trait 
 that previous methods struggle t...\n\n\nNuri Ryu, Minsu Gong, and Geonung
  Kim (POSTECH); Joo-Haeng Lee (Pebblous Inc.); and Sunghyun Cho (POSTECH, 
 Pebblous Inc.)\n---------------------\nNeural Stochastic Poisson Surface R
 econstruction\n\nReconstructing a surface from a point cloud is an underde
 termined problem. We propose using a neural network to study and quantify 
 this reconstruction uncertainty under a Poisson smoothness prior. Our algo
 rithm addresses the main limitations of existing work and can be fully int
 egrated into the 3D s...\n\n\nSilvia Sellán (University of Toronto) and Al
 ec Jacobson (University of Toronto, Adobe Research)\n---------------------
 \nReach For the Spheres: Tangency-aware surface reconstruction of SDFs\n\n
 Signed distance fields (SDFs) are a widely utilized implicit surface repre
 sentation that has applications in various fields such as computer graphic
 s, computer vision, and applied mathematics. Despite their frequent use, t
 raditional methods such as Marching Cubes and its variants often overlook 
 fund...\n\n\nSilvia Sellán (University of Toronto), Christopher Batty (Uni
 versity of Waterloo), and Oded Stein (University of Southern California)\n
 ---------------------\nRobust Zero Level-Set Extraction from Unsigned Dist
 ance Fields Based on Double Covering\n\nIn this paper, we propose a new me
 thod, called DoubleCoverUDF, for extracting the zero level-set from unsign
 ed distance fields (UDFs). DoubleCoverUDF takes a learned UDF and a user-s
 pecified parameter r (a small positive real number) as input and extracts 
 an iso-surface with an iso-value r using the...\n\n\nFei Hou (Institute of
  Software, Chinese Academy of Sciences; University of Chinese Academy of S
 ciences); Xuhui Chen and Wencheng Wang (Institute of Software, Chinese Aca
 demy Of Sciences; University of Chinese Academy of Sciences); Hong Qin (St
 ony Brook University); and Ying He (Nanyang Technological University)\n\nR
 egistration Category: Full Access\n\nSession Chair: Baoquan Chen (Peking U
 niversity)
END:VEVENT
END:VCALENDAR