Variational Depth from Focus Reconstruction
This work addresses depth estimation for computer vision applications, but it is incremental, building on existing variational and ADMM approaches.
The paper tackles depth map reconstruction from differently focused images by formulating it as a variational problem with a nonconvex data term and convex regularization, resulting in improved robustness to noise and more realistic depth maps, as validated through numerical comparisons on simulated and real data.
This paper deals with the problem of reconstructing a depth map from a sequence of differently focused images, also known as depth from focus or shape from focus. We propose to state the depth from focus problem as a variational problem including a smooth but nonconvex data fidelity term, and a convex nonsmooth regularization, which makes the method robust to noise and leads to more realistic depth maps. Additionally, we propose to solve the nonconvex minimization problem with a linearized alternating directions method of multipliers (ADMM), allowing to minimize the energy very efficiently. A numerical comparison to classical methods on simulated as well as on real data is presented.