Fast Organization and Dense Reconstruction of the World from Photo Collections

Опубликовано 17 августа 2016, 22:31

In recent years photo sharing web sites like Flickr have become increasingly popular. Nowadays, every day millions of photos are uploaded. These photos survey large parts of the world throughout the different seasons, various weather conditions and various times of the day. Given the scale of data we are facing significant challenges to process them within a reasonable time frame with limited resources. In the talk I will present my work on the highly efficient organization and reconstruction of 3D models from of city scale (millions of images) photo collections on a single PC in the span of a day. The approach addresses a variety of the current challenges that have to be addressed to achieve a concurrent 3D model from these data. The challenges are: selecting the data of interest from the noisy datasets, efficient robust camera motion estimation for (quasi- )degenerate estimation problems, high performance stereo estimation from multiple views, image based location recognition for topology detection. In the talk I will discuss the details of our optimal appearance and geometry based image organization method, our efficient stereo technique for determining the scene depths from photo collection images will also be explained during the talk. It allows to perform the scene depth estimation with multiple frames per second from a large set of views with a considerable variation in appearance. I will discuss some of the lessons learned for how to approach these large scale challenges in the future.