High Fidelity Image-Based Modeling

Google Tech Talks August 9, 2007 ABSTRACT In this talk, I will propose a novel algorithm for calibrated multi-view stereopsis that outputs a (quasi) dense set of rectangular patches covering the surfaces visible in the input images. This algorithm does not require any initialization in the form of a bounding volume, and it detects and discards automatically outliers and obstacles. It does not perform any smoothing across nearby features, yet is currently the top performer in terms of both coverage and accuracy for four of the six benchmarkdat asets presented in the Multi-View Stereo Evaluation (http://vision.middlebury.edu/mview/eval/). The keys to its performance are effective techniques for...