in: Contemporary Topics in Computer Graphics and Games, Veysi İşler,Haşmet Gürçay,Hasan Kemal Süher,Güven Çatak, Editor, Peter Lang Publishing, Inc., Berlin, pp.26, 2020
In this paper, a system is proposed to automatically generate 3D model of fountains from a single image. Although a single image is usually not sufficient for determining the 3D structure in an image; here we utilize our prior knowledge of general characteristic structures of fountains over the history such as the similarity of their top parts and their symmetrical shape. Firstly, object is detected and labelled on image using Convolutional Neural Networks (CNNs). Then, the object is segmented from background with Graph Cut technique and the contour of the object is used to estimate the shape of 3D model. Finally, 3D model of the fountain is completed by applying the texture acquired from the input image.