Improving Multi-View Stereo via Super-Resolution

Today, Multi-View Stereo techniques can reconstruct robust and detailed 3D models, especially when starting from high-resolution images. However, there are cases in which the resolution of input images is relatively low, for instance, when dealing with old photos or when hardware constrains the amount of data acquired. This paper shows how increasing the resolution of such input images through Super-Resolution techniques reflects in quality improvements of the reconstructed 3D models. We show that applying a Super-Resolution step before recovering the depth maps leads to a better 3D model both in the case of patchmatch and deep learning Multi-View Stereo algorithms. In detail, the use of Super-Resolution improves the average fl score of reconstructed models. It turns out to be particularly effective in the case of scenes rich in texture, such as outdoor landscapes.