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_480@linklings.com
SUMMARY:A Neural Implicit Representation for the Image Stack: Depth, All i
 n Focus, and High Dynamic Range
DESCRIPTION:Chao Wang (Max-Planck-Institut für Informatik); Ana Serrano (U
 niversidad de Zaragoza); and Xingang Pan, Bin Chen, Hans-Peter Seidel, Kar
 ol Myszkowski, Christian Theobalt, Krzysztof Wolski, and Thomas Leimkühler
  (Max-Planck-Institut für Informatik)\n\nIn everyday photography, physical
  limitations of camera sensors and lenses frequently lead to a variety of 
 degradations in captured images such as saturation or defocus blur. A comm
 on approach to overcome these limitations is to resort to image stack fusi
 on, which involves capturing multiple images with different focal distance
 s or exposures. For instance, to obtain an all-in-focus image, a set of mu
 lti-focus images is captured. Similarly, capturing multiple exposures allo
 ws for the reconstruction of high dynamic range (HDR).\nIn this paper, we 
 present a novel approach that combines neural fields with an expressive ca
 mera model to achieve a unified reconstruction of an all-in-focus HDR imag
 e from an image stack. \nOur approach is composed of a set of specialized 
 neural fields tailored to address specific sub-problems along our pipeline
 :\nWe use fields to predict flow to overcome misalignments arising from le
 ns breathing, depth and all-in-focus images to account for depth of field,
  as well as tonemapping to deal with sensor responses and saturation -- al
 l trained using a physically inspired supervision structure with a differe
 ntiable thin lens model at its core.\nAn important benefit of our approach
  is its ability to handle these tasks simultaneously or independently, pro
 viding flexible post-editing capabilities such as refocusing and exposure 
 adjustment.\nBy sampling the three primary factors in photography within o
 ur framework (focal distance, aperture, and exposure time), we conduct a t
 horough exploration to gain valuable insights into their significance and 
 impact on the overall image quality. \nThrough extensive validation, we de
 monstrate that our method outperforms existing approaches in both depth-fr
 om-defocus and all-in-focus image reconstruction tasks. Moreover, our appr
 oach exhibits promising results in each of these three dimensions, showcas
 ing its potential to enhance captured image quality and provide greater co
 ntrol in post-processing.\n\nRegistration Category: Full Access, Enhanced 
 Access, Trade Exhibitor, Experience Hall Exhibitor\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_480&sess=sess209
END:VEVENT
END:VCALENDAR