A novel three dimensional reconstruction framework from wide baseline images was proposed based on point and line features. After detecting and matching features, the relations between discrete images are computed and refined according to multi-view geometric constraints, and both structure of the scene and motion of cameras are retrieved, where we employ a procedure of Euclidean reconstruction based on approximate camera internal parameters and buddle adjustments. Based on retrieved motion and correspondence of line features, a 3D line reconstruction scheme was put forward to assist us in gaining regular structure and topology of the scene. In virtue of some manual interactions, mesh models of the scene came into being, and a rectification method for perspective images was used to acquiring texture patches. Finally, an interactive modeling prototype system from multiple images is designed and implemented. Real scenes and augmented reality applications demonstrate the feasibility, correctness and accuracy of our framework.