This dissertation investigates the general structure from motion problem. That is, how to compute in an unconstrained environment 3D scene structure, camera motion and moving objects from video sequences. We present a framework which uses concatenated feed-back loops to overcome the main difficulty in the structure from motion problem: the chicken-and-egg dilemma between scene segmentation and structure recovery. The idea is that we compute structure and motion in stages by gradually computing 3D scene information of increasing complexity and using processes which operate on increasingly large spatial image areas. Within this framework, we developed three modules. First, we introduce a new constraint for the estimation of shape using image features from multiple views. We analyze this constraint and show that noise leads to unavoidable mis-estimation of the shape, which also predicts the erroneous shape perception in human. This insight provides a clear argument for the need for feed-back loops. Second, a novel constraint on shape is developed which allows us to connect multiple frames in the estimation of camera motion by matching only small image patches. Third, we present a texture descriptor for matching areas of extended sizes. The advantage of this texture descriptor, which is based on fractal geometry, lies in its invariance to any smooth mapping (Bi-Lipschitz transform) including changes of viewpoint, illumination and surface distortion. Finally, we apply our framework to the problem of super-resolution imaging. We use the 3D motion estimation together with a novel wavelet-based reconstruction scheme to reconstruct a high-resolution image from a sequence of low-resolution images.