Single image depth estimation using joint local-global features

Hoda Mohaghegh, Nader Karimi, S.M.R. Soroushmehr, S. Samavi, K. Najarian

Research output: Chapter in Book/Conference paperConference paperpeer-review

3 Citations (Scopus)


Inferring scene depth from a single monocular image is an essential component in several computer vision applications such as 3D modeling and robotics. This process is an ill-posed problem. To tackle this challenging problem, previous efforts have been focusing on exploiting only global or local depth aware properties. We propose a model that incorporates both of them to obtain significantly more accurate depth estimates than using either global or local properties alone. Specifically, we formulate single image depth estimation as a K nearest neighbor search problem at both image level and patch level. At each level, a set of rich depth aware features, describing monocular depth cues, is employed in a nearest-neighbor regression model. By comparing the results with and without patch based fusion, the importance of our joint local-global framework becomes clear. The experimental results also demonstrate superior performance compared with existing data-driven approaches in both quantitative and qualitative analyses with a significantly simpler algorithm than others.
Original languageEnglish
Title of host publication2016 23rd International Conference on Pattern Recognition, ICPR 2016
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages6
ISBN (Electronic)9781509048472
Publication statusPublished - 1 Jan 2016
Externally publishedYes
Event23rd International Conference on Pattern Recognition - Cancun, Mexico
Duration: 4 Dec 20168 Dec 2016

Publication series

NameProceedings - International Conference on Pattern Recognition
ISSN (Print)1051-4651


Conference23rd International Conference on Pattern Recognition
Abbreviated titleICPR 2016


Dive into the research topics of 'Single image depth estimation using joint local-global features'. Together they form a unique fingerprint.

Cite this