Structure-aware depth super-resolution using Gaussian mixture model

Sunok Kim, Changjae Oh, Youngjung Kim, Kwanghoon Sohn

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)


This paper presents a probabilistic optimization approach to enhance the resolution of a depth map. Conventionally, a high-resolution color image is considered as a cue for depth super-resolution under the assumption that the pixels with similar color likely belong to similar depth. This assumption might induce a texture transferring from the color image into the depth map and an edge blurring artifact to the depth boundaries. In order to alleviate these problems, we propose an efficient depth prior exploiting a Gaussian mixture model in which an estimated depth map is considered to a feature for computing affinity between two pixels. Furthermore, a fixed-point iteration scheme is adopted to address the non-linearity of a constraint derived from the proposed prior. The experimental results show that the proposed method outperforms state-of-the-art methods both quantitatively and qualitatively.

Original languageEnglish
Title of host publicationProceedings of SPIE-IS and T Electronic Imaging - Three-Dimensional Image Processing, Measurement (3DIPM), and Applications 2015
EditorsRobert Sitnik, William Puech
ISBN (Electronic)9781628414837
Publication statusPublished - 2015
EventThree-Dimensional Image Processing, Measurement (3DIPM), and Applications 2015 - San Francisco, United States
Duration: 2015 Feb 102015 Feb 12

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X


OtherThree-Dimensional Image Processing, Measurement (3DIPM), and Applications 2015
Country/TerritoryUnited States
CitySan Francisco

Bibliographical note

Publisher Copyright:
© 2015 SPIE-IS&T.

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering


Dive into the research topics of 'Structure-aware depth super-resolution using Gaussian mixture model'. Together they form a unique fingerprint.

Cite this