Defocus Map Estimation

Proposta
07 Maggio 2014
Recovering the depth from a single defocused image
Voti totali: 0
Recovering the depth from a single defocused image

Blur - Song 2

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.

References: 

Shaojie Zhuo and Terence Sim, Defocus Map Estimation from a Single Defocused Image, Pattern Recognition, volume 44, number 9, pages 1852-1858, 2011

Shaojie Zhuo and Terence Sim, On the Recovery of Depth from a Single Defocused Image, International Conference on Computer Analysis of Images and Patterns (CAIP) 2009.