Depth up-sampling for depth coding using view information

Abstract

In 3DTV and free viewpoint imaging systems based on a view-plus-depth representation, depth compression is important for high-quality view synthesis. Several publications have proposed depth down-/up-sampling as part of the depth coding strategy. Recently, we proposed a depth up-sampling method which uses the high resolution view in the process of depth up-sampling. Actually, in 2007 Kopf et.al. already proposed a Joint Bilateral Upsampler(JBU), which uses a high resolution input image as prior in a joint bilateral filter for upscaling. In this paper we compare our previous method with the JBU approach, in the context of depth coding. Furthermore, we analyze the influence of view coding on the depth up-sampling result.