In this talk I will present an overview of several techniques developed in my group for recovering 3D shape, motion and appearance from images. We will start by discussing how to recover photo-realistic 3D models of static objects or scenes from videos. Besides static scenes, we also aim to model dynamic events. While we will show that it is possible to recover dynamic shape from a single video stream, the simplest way to recover dynamic shapes consists of using multiple cameras. Our approach allows for camera calibration and synchronization to be obtained from videos recorded during normal operation. Our silhouette-based technique recovers the 3D shape of multiple dynamic objects as well as of static occluding objects in the environment. Towards the future, one of our main research goals is to develop approaches for capturing immersive 4D spatio-temporal representation of dynamic events taking place in large-scale environments.