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:20240214T070244Z
LOCATION:Meeting Room C4.11\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231213T141500
DTEND;TZID=Australia/Melbourne:20231213T142500
UID:siggraphasia_SIGGRAPH Asia 2023_sess128_papers_524@linklings.com
SUMMARY:SimpleNeRF: Regularizing Sparse Input Neural Radiance Fields with 
 Simpler Solutions
DESCRIPTION:Technical Papers\n\nNagabhushan Somraj, Adithyan Karanayil, an
 d Rajiv Soundararajan (Indian Institute of Science)\n\nNeural Radiance Fie
 lds (NeRF) show impressive performance for the photo-realistic free-view r
 endering of scenes. However, NeRFs require dense sampling of images in the
  given scene, and their performance degrades significantly when only a spa
 rse set of views are available. Researchers have found that supervising th
 e depth estimated by the NeRF helps train it effectively with fewer views.
  The depth supervision is obtained either using classical approaches or ne
 ural networks pre-trained on a large dataset. While the former may provide
  only sparse supervision, the latter may suffer from generalization issues
 . As opposed to the earlier approaches, we seek to learn the depth supervi
 sion by designing augmented models and training them along with the NeRF. 
 We design augmented models that encourage simpler solutions by exploring t
 he role of positional encoding and view-dependent radiance in training the
  few-shot NeRF.  The depth estimated by these simpler models is used to su
 pervise the NeRF depth estimates.  Since the augmented models can be inacc
 urate in certain regions, we design a mechanism to choose only reliable de
 pth estimates for supervision. Finally, we add a consistency loss between 
 the coarse and fine multi-layer perceptrons of the NeRF to ensure better u
 tilization of hierarchical sampling. We achieve state-of-the-art view-synt
 hesis performance on two popular datasets by employing the above regulariz
 ations.\n\nRegistration Category: Full Access\n\nSession Chair: Jianfei Ca
 i (Monash University)
URL:https://asia.siggraph.org/2023/full-program?id=papers_524&sess=sess128
END:VEVENT
END:VCALENDAR