Abstract
This paper introduces an approach for dense 3D reconstruc- tion from unregistered Internet-scale photo collections with about 3 mil- lion images within the span of a day on a single PC (“cloudless”). Our method advances image clustering, stereo, stereo fusion and structure from motion to achieve high computational performance. We leverage geometric and appearance constraints to obtain a highly parallel imple- mentation on modern graphics processors and multi-core architectures. This leads to two orders of magnitude higher performance on an order of magnitude larger dataset than competing state-of-the-art approaches.