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_524@linklings.com
SUMMARY:SimpleNeRF: Regularizing Sparse Input Neural Radiance Fields with 
 Simpler Solutions
DESCRIPTION:Nagabhushan Somraj, Adithyan Karanayil, and Rajiv Soundararaja
 n (Indian Institute of Science)\n\nNeural Radiance Fields (NeRF) show impr
 essive performance for the photo-realistic free-view rendering of scenes. 
 However, NeRFs require dense sampling of images in the given scene, and th
 eir performance degrades significantly when only a sparse set of views are
  available. Researchers have found that supervising the depth estimated by
  the NeRF helps train it effectively with fewer views. The depth supervisi
 on is obtained either using classical approaches or neural networks pre-tr
 ained on a large dataset. While the former may provide only sparse supervi
 sion, the latter may suffer from generalization issues. As opposed to the 
 earlier approaches, we seek to learn the depth supervision by designing au
 gmented models and training them along with the NeRF. We design augmented 
 models that encourage simpler solutions by exploring the role of positiona
 l encoding and view-dependent radiance in training the few-shot NeRF.  The
  depth estimated by these simpler models is used to supervise the NeRF dep
 th estimates.  Since the augmented models can be inaccurate in certain reg
 ions, we design a mechanism to choose only reliable depth estimates for su
 pervision. Finally, we add a consistency loss between the coarse and fine 
 multi-layer perceptrons of the NeRF to ensure better utilization of hierar
 chical sampling. We achieve state-of-the-art view-synthesis performance on
  two popular datasets by employing the above regularizations.\n\nRegistrat
 ion Category: Full Access, Enhanced Access, Trade Exhibitor, Experience Ha
 ll Exhibitor\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_524&sess=sess209
END:VEVENT
END:VCALENDAR