In inverse problems, prior information and a priori-based regularization techniques play
important roles. In this paper, we focus on image restoration problems, especially on …

Shape from shading (SfS) and stereo are two fundamentally different strategies for image-
based 3-D reconstruction. While approaches for SfS infer the depth solely from pixel …

Variational approaches form an inherent part of most state-of-the-art pipeline approaches for
optical flow computation. As the final step of the pipeline, the aim is to refine an initial flow …

A recently suggested regularization method, which combines directional information with
total generalized variation (TGV), has been shown to be successful for restoring Gaussian …

Approaches based on order-adaptive regularisation belong to the most accurate variational
methods for computing the optical flow. By locally deciding between first-and second-order …

Shape from shading (SfS) and stereo are two fundamentally different strategies for image-
based 3-D reconstruction. While approaches for SfS infer the depth solely from pixel …

In variational optical flow estimation, second order regularisation plays an important role,
since it offers advantages in the context of non-fronto-parallel motion. However, in contrast to …

Recent approaches for variational motion estimation typically either rely on first or second
order regularisation strategies. While first order strategies are more appropriate for scenes …

Pipeline approaches that interpolate and refine an initial set of point correspondences have
recently shown a good performance in the field of optical flow estimation. However, so far …

Variational optical flow estimation, ie the estimation of motion information from image
sequences using continuous optimization approaches, plays an important role in computer …