BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260817T171536Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241204T113100
DTEND;TZID=Asia/Tokyo:20241204T114300
UID:siggraphasia_SIGGRAPH Asia 2024_sess113_papers_847@linklings.com
SUMMARY:Neural Light Spheres for Implicit Image Stitching and View Synthes
 is
DESCRIPTION:Ilya Chugunov and Amogh Joshi (Princeton University), Kiran Mu
 rthy and Francois Bleibel (Google Inc.), and Felix Heide (Princeton Univer
 sity)\n\nChallenging to capture, and challenging to display on a cellphone
  screen, the panorama paradoxically remains both a staple and underused fe
 ature of modern mobile camera applications. In this work we address both o
 f these challenges with a spherical neural light field model for implicit 
 panoramic image stitching and re-rendering; able to accommodate for depth 
 parallax, view-dependent lighting, and local scene motion and color change
 s during capture. Fit during test-time to an arbitrary path panoramic vide
 o capture -- vertical, horizontal, random-walk -- these neural light spher
 es jointly estimate the camera path and a high-resolution scene reconstruc
 tion to produce novel wide field-of-view projections of the environment. O
 ur single-layer model avoids expensive volumetric sampling, and decomposes
  the scene into compact view-dependent ray offset and color components, wi
 th a total model size of 80 MB per scene, and real-time (50 FPS) rendering
  at 1080p resolution. We demonstrate improved reconstruction quality over 
 traditional image stitching and radiance field methods, with significantly
  higher tolerance to scene motion and non-ideal capture settings.\n\nRegis
 tration Category: Full Access, Full Access Supporter\n\nLanguage Format: E
 nglish Language\n\nSession Chair: Forrester Cole (Google)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_847&sess=sess113
END:VEVENT
END:VCALENDAR