Analysis and improvement of joint bilateral upsampling for depth image super-resolution

Yibing Song*, Lijun Gong

*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

5 Citations (Scopus)

Abstract

We analyze and propose an improved implementation of joint bilateral upsampling algorithm [5] for depth image super-resolution (SR). The input to the algorithm is a low resolution (LR) depth image and its corresponding high resolution (HR) color image. With the guidance of HR color image, the depth edges can be preserved during the SR process. However, in the original implementation, the sparse sampling operation on the HR color image leads noticeable staircase effect on the generated result. In this paper, we perform a detailed analysis of the original implementation and formulate it as the joint bilateral filtering and nearest neighbor upsampling process. An improved implementation is then proposed to perform dense sampling on the guidance image. It will reduce staircase effect and demonstrated effective both quantitatively and qualitatively in the benchmark dataset.
Original languageEnglish
Title of host publication2016 8th International Conference on Wireless Communications and Signal Processing, WCSP 2016
PublisherIEEE
ISBN (Print)9781509028603
DOIs
Publication statusPublished - 21 Nov 2016
Event8th International Conference on Wireless Communications and Signal Processing, WCSP 2016 - Yangzhou, China
Duration: 13 Oct 201615 Oct 2016

Publication series

NameInternational Conference on Wireless Communications and Signal Processing
PublisherIEEE
ISSN (Print)2325-3746

Conference

Conference8th International Conference on Wireless Communications and Signal Processing, WCSP 2016
PlaceChina
CityYangzhou
Period13/10/1615/10/16

Research Keywords

  • Joint Bilateral Filter
  • Super-Resolution

Fingerprint

Dive into the research topics of 'Analysis and improvement of joint bilateral upsampling for depth image super-resolution'. Together they form a unique fingerprint.

Cite this