Edge-aware Bi-directional Diffusion for Dense Depth Estimation from Light Fields

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 143
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorKhan, Numairko
dc.contributor.authorKim, Min Hyukko
dc.contributor.authorTompkin, Jamesko
dc.date.accessioned2021-12-15T06:47:46Z-
dc.date.available2021-12-15T06:47:46Z-
dc.date.created2021-12-10-
dc.date.created2021-12-10-
dc.date.issued2021-11-22-
dc.identifier.citationThe 32nd British Machine Vision Conference, BMVC 2021-
dc.identifier.urihttp://hdl.handle.net/10203/290672-
dc.description.abstractWe present an algorithm to estimate fast and accurate depth maps from light fields via a sparse set of depth edges and gradients. Our proposed approach is based around the idea that true depth edges are more sensitive than texture edges to local constraints, and so they can be reliably disambiguated through a bidirectional diffusion process. First, we use epipolar-plane images to estimate sub-pixel disparity at a sparse set of pixels. To find sparse points efficiently, we propose an entropy-based refinement approach to a line estimate from a limited set of oriented filter banks. Next, to estimate the diffusion direction away from sparse points, we optimize constraints at these points via our bidirectional diffusion method. This resolves the ambiguity of which surface the edge belongs to and reliably separates depth from texture edges, allowing us to diffuse the sparse set in a depth-edge and occlusion-aware manner to obtain accurate dense depth maps.-
dc.languageEnglish-
dc.publisherThe British Machine Vision Association-
dc.titleEdge-aware Bi-directional Diffusion for Dense Depth Estimation from Light Fields-
dc.typeConference-
dc.type.rimsCONF-
dc.citation.publicationnameThe 32nd British Machine Vision Conference, BMVC 2021-
dc.identifier.conferencecountryUK-
dc.identifier.conferencelocationOnline-
dc.contributor.localauthorKim, Min Hyuk-
dc.contributor.nonIdAuthorKhan, Numair-
dc.contributor.nonIdAuthorTompkin, James-
Appears in Collection
CS-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0