Related Researcher

Author's Photo

Sim, Jae-Young
Visual Information Processing Lab (VIP Lab)
Research Interests
  • Image processing, computer vision, 3D visual processing, signal processing


FDQM: fast quality metric for depth maps without view synthesis

DC Field Value Language Jang, Won-Dong ko Chung, Tae-Young ko Sim, Jae-Young ko Kim, Chang-Su ko 2015-07-29T00:53:17Z - 2015-07-24 ko 2015-07 ko
dc.identifier.citation IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, v.25, no.7, pp.1099 - 1112 ko
dc.identifier.issn 1051-8215 ko
dc.identifier.uri -
dc.description.abstract We propose a fast quality metric for depth maps, called fast depth quality metric (FDQM), which efficiently evaluates the impacts of depth map errors on the qualities of synthesized intermediate views in multiview video plus depth applications. In other words, the proposed FDQM assesses view synthesis distortions in the depth map domain, without performing the actual view synthesis. First, we estimate the distortions at pixel positions, which are specified by reference disparities and distorted disparities, respectively. Then, we integrate those pixel-wise distortions into an FDQM score by employing a spatial pooling scheme, which considers occlusion effects and the characteristics of human visual attention. As a benchmark of depth map quality assessment, we perform a subjective evaluation test for intermediate views, which are synthesized from compressed depth maps at various bitrates. We compare the subjective results with objective metric scores. Experimental results demonstrate that the proposed FDQM yields highly correlated scores to the subjective ones. Moreover, FDQM requires at least 10 times less computations than conventional quality metrics, since it does not perform the actual view synthesis. ko
dc.description.statementofresponsibility close -
dc.language 영어 ko
dc.title FDQM: fast quality metric for depth maps without view synthesis ko
dc.type ARTICLE ko
dc.identifier.scopusid 2-s2.0-84936774635 ko
dc.identifier.wosid 000357616600002 ko
dc.type.rims ART ko
dc.description.wostc 0 *
dc.description.scopustc 0 * 2015-12-28 * 2015-11-04 *
dc.identifier.doi 10.1109/TCSVT.2014.2372343 ko
dc.identifier.url ko
Appears in Collections:
AI_Journal Papers
Files in This Item:
There are no files associated with this item.

find_unist can give you direct access to the published full text of this article. (UNISTARs only)

Show simple item record


  • mendeley


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.