A Solution for Scale Ambiguity in Generative Novel View Synthesis

Simple item page
dc.contributor.advisorBrubaker, Marcus
dc.contributor.authorForghani, Fereshteh
dc.date.accessioned2025-04-10T10:57:32Z
dc.date.available2025-04-10T10:57:32Z
dc.date.copyright2025-01-07
dc.date.issued2025-04-10
dc.date.updated2025-04-10T10:57:31Z
dc.degree.disciplineComputer Science
dc.degree.levelMaster's
dc.degree.nameMSc - Master of Science
dc.description.abstractGenerative Novel View Synthesis (GNVS) involves generating plausible unseen views of a scene given an initial view and the relative camera motion between the input and target views using generative models. A key limitation of current generative methods lies in their susceptibility to scale ambiguity, an inherent challenge in multi-view datasets caused by the use of monocular techniques to estimate camera positions from uncalibrated video frames. In this work, we present a novel approach to tackle this scale ambiguity in multi-view GNVS by optimizing the scales as parameters in an end-to-end fashion. We also introduce Sample Flow Consistency (SFC), a novel metric designed to assess scale consistency across samples with the same camera motion. Through various experiments, we demonstrate our approach yields improvements in terms of SFC, providing more consistent and reliable novel view synthesis.
dc.identifier.urihttps://hdl.handle.net/10315/42872
dc.languageen
dc.rightsAuthor owns copyright, except where explicitly noted. Please contact the author directly with licensing requests.
dc.subject.keywordsScale ambiguity
dc.subject.keywordsNovel view synthesis
dc.subject.keywordsGenerative
dc.subject.keywordsDiffusion
dc.subject.keywordsMulti-view
dc.titleA Solution for Scale Ambiguity in Generative Novel View Synthesis
dc.typeElectronic Thesis or Dissertation

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Forghani_Fereshteh_2025_MSc.pdf
Size:
14.37 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
license.txt
Size:
1.87 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
YorkU_ETDlicense.txt
Size:
3.39 KB
Format:
Plain Text
Description:
Download

Collections

Computer Science

All items in the YorkSpace institutional repository are protected by copyright, with all rights reserved except where explicitly noted.