An Interactive 2D-to-3D Cartoon Modeling System
In this paper, we propose an interactive system that can quickly convert a 2D cartoon painting into a 3D textured cartoon model, enabling non-professional adults and children to easily create personalized 3D contents. Our system exploits a new approach ba
- PDF / 1,707,059 Bytes
- 12 Pages / 439.37 x 666.142 pts Page_size
- 59 Downloads / 198 Views
Abstract. In this paper, we propose an interactive system that can quickly convert a 2D cartoon painting into a 3D textured cartoon model, enabling non-professional adults and children to easily create personalized 3D contents. Our system exploits a new approach based on solving Poisson equations to generate 3D models, which is free from the limitations of spherical topology in prior works. We also propose a novel method to generate whole textures for both sides of the models to deliver colorful appearances, making it possible to obtain stylized models rendered with cartoon textures. The results have shown that our method can greatly simplify the modeling process comparing with both traditional modeling softwares and prior sketch-based systems. Keywords: Modeling interface Deformation Texture Interactive modeling
1 Introduction The demand for personalized 3D models is rapidly growing with the increasing applications of emerging technologies like 3D printing and augmented reality. However, for novice users, it is difficult to build 3D models using professional modeling systems. Traditional 3D modeling tools, such as Maya [1] and 3ds Max [2] require users to learn a complicated interface, which are daunting challenges for novice users. In order to simplify the 3D modeling pipeline, sketch-based modeling systems, such as Teddy [3] and its follow-up works [4–8] presented approaches to create 3D models from 2D strokes. However, these systems have some common limitations. First, most of these systems require users to sketch from a large number of different views, making it difficult for novice users to complete their tasks. Second, these systems cannot generate models from 2D cartoon images directly and only use them as the guide images. In order to create desired models, users have to draw carefully to make their sketch match with the silhouettes in guide images. As a result, the silhouettes of the final shape may differ from the input sketch, which may be undesired. Third, shapes that can be handled by these systems are also limited. For example, they do not allow cycles of connection curves. Surfaces with edges or flat surfaces also cannot be generated directly. Finally, models generated by these systems lack texture information, thus the rendering of these models cannot take advantage of the original paintings. Unlike sketch-based systems, Ink-and-Ray [9] involves Poisson equations to produce bas-relief meshes, which can support global illumination effects for hand-drawn characters. However, the resulted © Springer International Publishing Switzerland 2016 A. El Rhalibi et al. (Eds.): Edutainment 2016, LNCS 9654, pp. 193–204, 2016. DOI: 10.1007/978-3-319-40259-8_17
194
L. Feng et al.
meshes are not full 3D models, which limit their usage and artifacts may appear when rendered with a perspective camera or from different views. The goal of our work is to design a system that allows creating full threedimensional models from two-dimensional cartoon images directly without requiring much input. Our system makes i
Data Loading...
