Rahul Raguram

TL;DR: This paper introduces an approach for dense 3D reconstruction from unregistered Internet-scale photo collections with about 3 million images within the span of a day on a single PC ("cloudless"), leveraging geometric and appearance constraints to obtain a highly parallel implementation on modern graphics processors and multi-core architectures.

TL;DR: The technique developed is capable of efficiently adapting to the constraints presented by a fixed time budget, while at the same time providing accurate estimation over a wide range of inlier ratios, and shows significant improvements in accuracy and speed over existing techniques.

TL;DR: A comprehensive overview of recent research in RANSAC-based robust estimation is presented by analyzing and comparing various approaches that have been explored over the years and introducing a new framework for robust estimation, which is called Universal RANSac (USAC).

TL;DR: This article presents an approach for modeling landmarks based on large-scale, heavily contaminated image collections gathered from the Internet that efficiently combines 2D appearance and 3D geometric constraints to extract scene summaries and construct 3D models.

TL;DR: The implications of the ubiquity of personal mobile devices are investigated and new techniques for compromising the privacy of users typing on virtual keyboards are revealed, highlighting the importance of adjusting privacy expectations in response to emerging technologies.