Recovering Depth from a Single Defocued Image

Overview

In this project, we address the challenging problem of recovering the depth from a single defocused image. We estimate a sparse depth map from the blur amount at each edge location and then propogate the depth estimates to the whole image and obtain the full depth map. An example is shown below.

Input Image
Sparse Depth Map
Full Depth Map

Abstract

In this paper, we address the challenging problem of recovering the depth from a single defocused image. We present a simple yet effective approach to estimate the amount of spatially varying defocus blur at edge locations. The input defocused image is re-blurred using a Gaussian kernel and the defocus blur amount can be obtained from the gradient ratio between the input and re-blurred images. By propagating the blur amount at edge locations to the entire image, the full depth map of the scene can be recovered. Experimental results on synthetic and real images demonstrate the effectiveness of our method in providing a reliable estimation of the depth of a scene.

Publications

Recovering Depth from a Single Defocused Image
Shaojie Zhuo and Terence Sim
Pattern Recognition (under review)
Draft PDF (7.3M) | Image Data

On the Recovery of Depth from a Single Defocused Image
Shaojie Zhuo and Terence Sim
International Conference on Computer Analysis of Images and Patterns (CAIP) 2009 (Oral, 33 of 410).
PDF (1.4M) | BibTeX | Slides

BibTeX

@inproceedings{ZhuoAndSim2010,
  author = {Shaojie Zhuo and Terence Sim},
  title = {On the Recovery of Depth from a Single Defocused Image},
  booktitle = {Processings of the 13th International Conference on Computer Analysis of Images and Patterns},
  year = {2009}
}