MVE – A Multi-View Reconstruction Environment

Figure 1: Our multi-view reconstruction pipeline. Starting from input images, structure-from-motion (SfM) techniques are used to reconstruct camera parameters and a sparse set of points. Depth maps are computed for every image using multi-view stereo (MVS). Finally, a colored mesh is extracted from the union of all depth maps using a surface reconstruction approach (FSSR). We present MVE, the Multi-View Environment. MVE is an end-to-end multi-view geometry reconstruction soft-ware which takes photos of a scene as input and produces a surface triangle mesh as result. The system covers a structure-from-motion algorithm, multi-view stereo reconstruction, generation of extremely dense point clouds, and reconstruction of surfaces from point clouds. In contrast to most image-based geometry reconstruction ap-proaches, our system is focused on reconstruction of multi-scale scenes, an important aspect in many areas such as cultural heritage. It allows to reconstruct large datasets containing some detailed regions with much higher resolution than the rest of the scene. Our system provides a graphical user interface for structure-from-motion reconstruction, visual inspection of images, depth maps, and rendering of scenes and meshes