Supplementary Material for A Multi-View Stereo Benchmark with High-Resolution Images and Multi-Camera Videos

We show images of all 14 initial scenes in our benchmark in Fig. 1. They consist of 7 outdoor and 7 indoor scenes. Numerous scenes contain thin structures such as the trees in forest, or a rope in playground. Several scenes also contain large homogeneous or reflective surfaces such as the floor in pipes and terrains, the walls in office, or some doors in electro. These elements make the scenes challenging for stereo algorithms. All DSLR and multi-camera rig datasets were recorded within those scenes. Fig. 2 and Fig. 3 show example images of the high-resolution multi-view stereo datasets, while Fig. 4 shows the two-view stereo datasets. We plan to extend the benchmark with additional datasets over time.