Sketch-Based Instancing of Parameterized 3D Models

نویسندگان

  • Dan Xiao
  • Zhigeng Pan
  • Renzhong Zhou
چکیده

We present a system for constructing 3D models from simple hand-drawn sketches. The system exploits a priori knowledge about the type of object being sketched. In particular, we assume that the class of object being drawn is known, (e.g., a rocket ship) and that the object will be drawn using a fixed number of known components. By using these assumptions, we show that we can build a sketch-based modeling system that, while object specific, is capable of quickly creating geometric models that are beyond the scope of current sketch-based modeling approaches. Key to our approach is the use of a K-means classifier for labeling each drawn stroke as being a particular component in the generic model. We demonstrate our approach by applying this classifier to face and rocket sketches.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Learning the parameters of quantitative prosody models

The article introduces a novel hybrid data driven and rule based approach for the prosody control in a TTS system, which combines the advantages of well-balanced, quantitative models with the flexible training of derived model parameters. Instancing the training of Fujisaki intonation parameters for German (MFGI) the article describes the hybrid data driven and rule based architecture HYDRA, th...

متن کامل

Automatic Detection and Large-Scale Visualization of Trees for Digital Landscapes and City Models Based on 3D Point Clouds

Vegetation objects represent one main compositional element of digital models of our environment required by a growing number of simulation, analysis, and visualization applications. However, a detailed representation of vegetation in 3D spatial models is generally not feasible due to the lack of up-to-date, object-based, and area-wide tree surveys and computational limits in data acquisition, ...

متن کامل

Scale-Dependent Simplification of 3D Building Models Based on Cell Decomposition and Primitive Instancing

The paper proposes a novel approach for a scale-dependent geometric simplification of 3D building models that are an integral part of virtual cities. In contrast to real-time photorealistic visualisations, map-like presentations emphasize the specific cartographic properties of objects. For buildings objects, such properties are e.g. the parallel and right-angled arrangements of facade walls an...

متن کامل

Generalisation of 3d Building Models by Cell Decomposition and Primitive Instancing

The article presents a cartographic generalisation approach for 3D building models with regard to the thematic visualisation of urban landscapes. Based on our earlier work to utilise approximating planes for generating simplified cell decompositions of the input objects, a new extension is introduced that guarantees well-formed roof structures. This is accomplished by first creating a simplifie...

متن کامل

Techniques for generating shape instances from domain distributed vague models

We are developing and implementing a novel method, called vague shape modeling, which is able to model geometric uncertainty by describing distribution domain of the shapes. In order to obtain shape instances, we have implemented specific instance generation operators that extract a set of boundary particles from the distribution domain based on predefined selection functions. In this paper, we...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2010