This paper tackles the active research problem of fast automatic modeling of large-scale environments from videos and unorganized still image collections. We describe a scalable 3D reconstruction framework that leverages recent research in robust estimation, image-based recognition, and stereo depth estimation. High computational speed is achieved through parallelization and execution on commodity graphics hardware. For video, we have implemented a reconstruction system that works in real time; for still photo collections, we have a system that is capable of processing thousands of images in less than a day on a single commodity computer. Modeling results from both systems are shown on a variety of large-scale real-world datasets.