Superpixel-based depth image super-resolution

Yongseok Soh, Jae Young Sim, Chang-Su Kim, Sang Uk Lee

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

13 Citations (Scopus)


Due to the development of depth sensors, such as time-of-flight (ToF) cameras, it becomes easier to acquire depth information directly from a scene. Although such devices enable us to obtain depth maps at video frame rates, the depth maps often have low resolutions only. A typical ToF camera retrieves depth maps of resolution 320 × 200, which is much lower than the resolutions of high definition color images. In this work, we propose a depth image super-resolution algorithm, which operates robustly even when there is a large resolution gap between a depth image and a reference color image. To prevent edge smoothing artifacts, which are the main drawback of conventional techniques, we adopt a superpixel-based approach and develop an edge enhancing scheme. Simulation results demonstrate that the proposed algorithm aligns the edges of a depth map to accurately coincide with those of a high resolution color image.

Original languageEnglish
Title of host publicationProceedings of SPIE-IS and T Electronic Imaging - Three-Dimensional Image Processing (3DIP) and Applications II
Publication statusPublished - 2012
Event3-Dimensional Image Processing (3DIP) and Applications II - Burlingame, CA, United States
Duration: 2012 Jan 242012 Jan 26

Publication series

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


Other3-Dimensional Image Processing (3DIP) and Applications II
Country/TerritoryUnited States
CityBurlingame, CA


  • Depth image
  • Depth map super-resolution
  • Image interpolation
  • Superpixel

ASJC Scopus subject areas

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


Dive into the research topics of 'Superpixel-based depth image super-resolution'. Together they form a unique fingerprint.

Cite this