Depth extraction from a single image based on block-matching and robust regression

Hyeongju Jeong, Changjae Oh, Youngjung Kim, Kwanghoon Sohn

Research output: Contribution to journalConference article

Abstract

Predicting scene depth (or geometric information) from single monocular images is a challenging task. This paper addresses such challenging and essentially ill-posed problem by regression on samples for which the depth is known. In this regard, we first retrieve semantically similar RGB and depth pairs from datasets using a deep convolutional activation feature. We show that our framework provides a richer foundation for depth estimation than existing hand-craft representations. Subsequently, an initial estimation is then integrated by block-matching and robust patch regression. It assigns perceptually appropriate depth values to an input query in accordance with a data-driven depth prior. A final post processor aligns depth maps with RGB discontinuities, resulting in visually plausible results. Experiments on the Make 3D and NYU RGB-D datasets show competitive results compared to recent state-of-The-Art methods.

Original languageEnglish
JournalIS and T International Symposium on Electronic Imaging Science and Technology
DOIs
Publication statusPublished - 2016 Jan 1
Event27th Annual Stereoscopic Displays and Applications Conference, SD and A 2016 - San Francisco, United States
Duration: 2016 Feb 142016 Feb 18

    Fingerprint

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design
  • Computer Science Applications
  • Human-Computer Interaction
  • Software
  • Electrical and Electronic Engineering
  • Atomic and Molecular Physics, and Optics

Cite this