A new approach is presented for 3D shape recovery of local planar surface patches from two shift/spacevariant defocused images. It is based on a recently proposed technique for inverting the shift-variant blurring in a camera system. It is completely localized, applicable to general point spread functions, and facilitates fine-grain parallel implementation and computationally efficient recovery of 3D shape. The shape of a visible object at each pixel is specified by the distance and slopes of a local planar surface patch that approximates the object surface at that pixel. The theory underlying the new approach and experimental results are presented. Results of both simulation and real experiments indicate that the new approach is effective and useful in practical applications.