Abstract

Curvature has received increasing attention as an important alternative to length based regularization in computer vision. In contrast to length, it preserves elongated structures and fifine details. Existing approaches are either ineffifi- cient, or have low angular resolution and yield results with strong block artifacts. We derive a new model for computing squared curvature based on integral geometry. The model counts responses of straight line triple cliques. The corresponding energy decomposes into submodular and supermodular pairwise potentials. We show that this energy can be effificiently minimized even for high angular resolutions using the trust region framework. Our results confifirm that we obtain accurate and visually pleasing solutions without strong artifacts at reasonable runtimes