Journal of Electrical and Computer Engineering / 2017 / Article / Fig 26

Research Article

Autofocus on Depth of Interest for 3D Image Coding

Figure 26

Visual quality comparison of synthesized view for (a) UndoDancer view 3 frame 250 using (b) uncompressed depth and texture; depth coded at 0.014 bpp and texture coded at 0.2 bpp (c) by classic LAR; (d) by the proposed DoI refinement of depth scheme and SNR quality enhancement of texture with a full-resolution DoI-Mask; (e) by the proposed DoI scheme with the block resolution DoI-Mask.
(a)
(b)
(c)
(d)
(e)

We are committed to sharing findings related to COVID-19 as quickly as possible. We will be providing unlimited waivers of publication charges for accepted research articles as well as case reports and case series related to COVID-19. Review articles are excluded from this waiver policy. Sign up here as a reviewer to help fast-track new submissions.