From Single Image Query to Detailed 3D Reconstruction
Structure-from-Motion for unordered image collections has significantly advanced in scale over the last decade. This impressive progress can be in part attributed to the introduction of efficient retrieval methods for those systems. While this boosts scalability, it also limits the amount of detail that the large-scale reconstruction systems are able to produce. In this paper, we propose a joint reconstruction and retrieval system that maintains the scalability of large-scale Structure-from-Motion systems while also recovering the often lost ability of reconstructing fine details of the scene. We demonstrate our proposed method on a large-scale dataset of 7.4 million images downloaded from the Internet.
This material is based upon work supported by the National Science Foundation under Grant No.IIS-1252921, IIS-1349074, IIS-1452851, CNS-1405847, and by the US Army Research, Development and Engineering Command Grant No.W911NF-14-1-0438. F. Radenovic and O. Chum were supported by MSMT LL1303 ERC-CZ grant.