All-in-focus image reconstruction with depth sensing

Abstract

In order to reconstruct the all-in-focus image from a conventional camera, a spatially-varying defocus deblurring approach based on blur map and TV/L2 regularization was proposed. Firstly, lenticular defocus model was studied and analyzed, and the principle, characteristic and applicability of disk defocus model and Gaussian defocus model were generalized; Secondly, we modified the local contrast prior using edge properties, and combined it with the gradient of blurry edge to gain blur map, in addition, in order to decrease the noise of blur map and ambiguous edges, a guided filtering approach was also adopted to gain a better blur map; Finally, TV/L2 regularization method solved by an augmented Lagrangian method was employed to deblur the defocus image. The all-in-focus image is obtained using scale selection and image reconstruction. The experimental results based on both synthesized images and real images showed that the proposed approach can gain excellent all-in-focus images and the performance outperforms the state-of-the-art space-invariant methods and spatially-varying methods for defocus deblurring, and the all-in-focus images show a better visual effect.