Thin Structure Estimation with Curvature Regularization
This addresses the challenge of accurately localizing thin structures in vision applications, which is incremental but with a novel optimization approach.
The paper tackles the problem of estimating thin structures like edges and vessels by simultaneously detecting and delineating them with sub-pixel localization and orientation estimation, using a novel algorithm that combines detection likelihoods with curvature regularization, achieving improved performance on 2D and 3D examples.
Many applications in vision require estimation of thin structures such as boundary edges, surfaces, roads, blood vessels, neurons, etc. Unlike most previous approaches, we simultaneously detect and delineate thin structures with sub-pixel localization and real-valued orientation estimation. This is an ill-posed problem that requires regularization. We propose an objective function combining detection likelihoods with a prior minimizing curvature of the center-lines or surfaces. Unlike simple block-coordinate descent, we develop a novel algorithm that is able to perform joint optimization of location and detection variables more effectively. Our lower bound optimization algorithm applies to quadratic or absolute curvature. The proposed early vision framework is sufficiently general and it can be used in many higher-level applications. We illustrate the advantage of our approach on a range of 2D and 3D examples.