Depth from defocus is a common method for recovering scene depth information. In traditional methods we usually need to collect multiple defocused images. However

this is difficult in practical application. In this paper

we address a challenging problem of recovering the depth from a single photograph taken with an uncalibrated conventional camera. In order to achieve this

we present a simple yet effective two-step approach to estimate the blur map of the input image. 1)A sparse blur map is obtained by estimating the amount of defocus blur at the edge locations. 2)Based on image segmentation and the sparse blur map to get the global blur map

complete depth information can be restorated. In order to obtain accurate scene depth information

we join geometry constraints

the sky area extraction and segmentation strategy to eliminate the impact of color

texture and focal plane ambiguity. Experimental results on a variety of images show that our method can acquire a reliable estimation of the depth of a scene.