Test‐Time Optimization for Video Depth Estimation Using Pseudo Reference Depth

Simple item page
dc.contributor.authorZeng, Libingen_US
dc.contributor.authorKalantari, Nima Khademien_US
dc.contributor.editorHauser, Helwig and Alliez, Pierreen_US
dc.date.accessioned2023-03-22T15:07:14Z
dc.date.available2023-03-22T15:07:14Z
dc.date.issued2023
dc.description.abstractIn this paper, we propose a learning‐based test‐time optimization approach for reconstructing geometrically consistent depth maps from a monocular video. Specifically, we optimize an existing single image depth estimation network on the test example at hand. We do so by introducing pseudo reference depth maps which are computed based on the observation that the optical flow displacement for an image pair should be consistent with the displacement obtained by depth‐reprojection. Additionally, we discard inaccurate pseudo reference depth maps using a simple median strategy and propose a way to compute a confidence map for the reference depth. We use our pseudo reference depth and the confidence map to formulate a loss function for performing the test‐time optimization in an efficient and effective manner. We compare our approach against the state‐of‐the‐art methods on various scenes both visually and numerically. Our approach is on average 2.5× faster than the state of the art and produces depth maps with higher quality.en_US
dc.description.number1
dc.description.sectionheadersArticles
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume42
dc.identifier.doi10.1111/cgf.14729
dc.identifier.issn1467-8659
dc.identifier.pages195-205
dc.identifier.urihttps://doi.org/10.1111/cgf.14729
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14729
dc.publisherEurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd.en_US
dc.subjectimage and video processing
dc.subjectcomputational photography
dc.titleTest‐Time Optimization for Video Depth Estimation Using Pseudo Reference Depthen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
v42i1pp195-205-cgf14729.pdf
Size:
3 MB
Format:
Adobe Portable Document Format
Download
Collections
42-Issue 1