I’m happy that our variational-depth-from-focus project that we developed during the Practical Course: GPU Programming in Computer Vision, is finally online. It is a CUDA implementation of “Variational Depth from Focus Reconstruction” [Moeller 2015]. Intro The whole idea is that you can get a depth map from a set of aligned, differently focused images. This technique can be used e.g. in movie productions to capture the static 3d geometry of a scene to add special effects later on or in microscopy to get an elevation map of the probe. Abstract 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. Example We recorded this sequence of 19 differently focused images http://in.tum.de/~haarbach/balcony.zip (19 images, 8.7MB) The first image of the sequence is shown below: After running our algorithm, we get the following smooth depth map:
I finally finished my bachelor’s thesis. Here is the final thesis as well as the final presentation slides. All the code I developed during research is open source and hosted in the ppf-reconstruction repository. Abstract This work aims at reconstructing
zum Artikel gehenIn2020werden wir mit der SegelyachtSanssouciein umfangreiches und spannendes Trnprogramm in derOst und Nordseesowie demNordatlantikmit dem Focus auf die Inselwelt derLofotenund dasNordkapanbieten. Die einzelnen Trnetappen sind in der Rubrik
Another Training Successfuly Completed With great satisfaction we congratulate the Department of Meteorological Services of Botswana team on their achievement in reaching the completion of the TriVis Weather Graphix and Website Training course performed f
zum Artikel gehenHome Case studies Henkel’s DevOps triumph – a boost of agility, clear focus and team engagement Henkel embarked on a journey to enhance quality and engagement across the
zum Artikel gehenHome Press Release Heleen Herselman joins Skaylink as Practice Lead AWS Skaylink is pleased to announce that Heleen Herselman h
zum Artikel gehen