Improving Multi-View Stereo via Super-Resolution
This addresses a practical issue for 3D reconstruction from old photos or hardware-limited data, but it is incremental as it combines existing methods.
The paper tackles the problem of low-resolution input images in Multi-View Stereo by applying Super-Resolution techniques, showing that this step improves 3D model quality, especially completeness in textured scenes.
Today, Multi-View Stereo techniques are able to 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 that can be acquired. In this paper, we investigate if, how, and how much increasing the resolution of such input images through Super-Resolution techniques reflects in quality improvements of the reconstructed 3D models, despite the artifacts that sometimes this may generate. We show that applying a Super-Resolution step before recovering the depth maps in most cases leads to a better 3D model both in the case of PatchMatch-based and deep-learning-based algorithms. The use of Super-Resolution improves especially the completeness of reconstructed models and turns out to be particularly effective in the case of textured scenes.