Abstract
This work proposes a progressive patch based multi-view stereo algorithm able to deliver a dense point cloudat any time. This enables an immediate feedback on the reconstruction process in a user centric scenario. With in-creasing processing time, the model is improved in termsof resolution and accuracy. The algorithm explicitly han-dles input images with varying effective scale and createsvisually pleasing point clouds. A priority scheme assuresthat the limited computational power is invested in scene parts, where the user is most interested in or the overall error can be reduced the most. The architecture of the proposed pipeline allows fast processing times in large scenesusing a pure open-source CPU implementation. We show the performance of our algorithm on challenging standard datasets as well as on real-world scenes and compare it to the baseline.