DeepMVS: Learning Multi-View Stereopsis
Po-Han Huang1 Kevin Matzen2 Johannes Kopf2 Narendra Ahuja1 Jia-Bin Huang3
1University of Illinois, Urbana Champaign 2Facebook 3Virginia Tech
Comparisons with Conventional MVS Algorithms
Below are the comparisons between our approach and other conventional multi-view stereo algorithms evaluated on ETH3D Dataset.
| Reference | Ground Truth | PMVS | MVE | COLMAP (filtered) | COLMAP (unfiltered) | Our Result |
|---|---|---|---|---|---|---|
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
