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:20260114T163633Z
LOCATION:Darling Harbour Theatre\, Level 2 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231212T093000
DTEND;TZID=Australia/Melbourne:20231212T124500
UID:siggraphasia_SIGGRAPH Asia 2023_sess209_papers_779@linklings.com
SUMMARY:ReShader: View-Dependent Highlights for Single Image View-Synthesi
 s
DESCRIPTION:Avinash Paliwal and Brandon G. Nguyen (Texas A&M University), 
 Andrii Tsarov (Leia Inc.), and Nima Khademi Kalantari (Texas A&M Universit
 y)\n\nIn recent years, novel view synthesis from a single image has seen s
 ignificant progress thanks to the rapid advancements in 3D scene represent
 ation and image inpainting techniques. While the current approaches are ab
 le to synthesize geometrically consistent novel views, they often do not h
 andle the view-dependent effects properly. Specifically, the highlights in
  their synthesized images usually appear to be glued to the surfaces, maki
 ng the novel views unrealistic. To address this major problem, we make a k
 ey observation that the process of synthesizing novel views requires chang
 ing the shading of the pixels based on the novel camera, and moving them t
 o appropriate locations. Therefore, we propose to split the view synthesis
  process into two independent tasks of pixel reshading and relocation. Dur
 ing the reshading process, we take the single image as the input and adjus
 t its shading based on the novel camera. This reshaded image is then used 
 as the input to an existing view synthesis method to relocate the pixels a
 nd produce the final novel view image. We propose to use a neural network 
 to perform reshading and generate a large set of synthetic input-reshaded 
 pairs to train our network. We demonstrate that our approach produces plau
 sible novel view images with realistic moving highlights on a variety of r
 eal world scenes.\n\nRegistration Category: Full Access, Enhanced Access, 
 Trade Exhibitor, Experience Hall Exhibitor\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_779&sess=sess209
END:VEVENT
END:VCALENDAR