Overview on 3D reconstruction from images

Abstract

In recent years, the world of computer graphics has made tremendous progress. Several 3D model visualization techniques have emerged and have been introduced in the hardware's. The machines on which are realized the 3D visualization have also evolved. We do not need expensive computers to see a world in 3D; a simple computer can do the trick. This evolution has also created a demand for visualizing models that are more complex and realistic. Historically, research has focused on the development of 3D information and acquisition techniques from scenes and objects. Demand has grown more in the field of computer graphics, virtual reality and communication. Acquiring 3D information's from real objects in a scene requires intricate calibration procedures every time the system is used. In addition, the use of these acquisition systems requires expertise by their users. This creates a significant demand for flexibility in acquisitions. These procedures must be absent or limited to a minimum. Because of these different factors, many techniques have been developed in recent years. Many of them only need a simple camera and a computer to be able to acquire 3D images.