A new approach to 3D shape recovery of local planar surface patches from shift-variant blurred images

Reconstruction of depth from 2D images is an important research issue in computer vision. Depth from defocus (DFD) technique uses space varying blurring of an image as a cue in reconstructing the 3D structure of a scene. In this paper we explore the regularization based approach for simultaneous estimation of depth and image restoration from defocused observations. We are given two defocused observations of a scene that are captured with different camera parameters. Our method consists of two steps. First we obtain the initial estimates for the depth as well as for the focused image. In the second step we refine the solution by using a fast optimization technique. Here we use the classic depth recovery method due to Subbarao for obtaining the initial depth map and Weiner filter approach for initial image restoration. Since the problem we are solving is ill-posed and does not yield unique solution, it is necessary to regularize the solution by imposing additional constraint to restrict the solution space. The regularization is performed by imposing smoothness constraint only. However, for preserving the depth and image intensity discontinuities, they are identified prior to the minimization process from initial estimates of the depth map and the restored image. The final solution is obtained by using computationally efficient gradient descent algorithm, thus avoiding the need for computationally taxing algorithms. The depth as well as intensity edge details of the final solution correspond to those obtained using the initial estimates. The experimental results indicate that the quality of the restored image is good even under severe space-varying blur conditions.

show abstract

A new approach to 3D shape recovery of local planar surface patches from shift-variant blurred images

Abstract: Abstract

Cited by 3 publications

References 9 publications

Shape Reconstruction from a Monocular Defocus Image Using CNN

Shape Reconstruction from a Monocular Defocus Image Using CNN

Auto-context modeling using multiple Kernel learning

A practical approach for depth estimation and image restoration using defocus cue

Contact Info

Product

Resources

About