Browsing 34-Issue 7 by Subject "I.3.5 [Computer Graphics]"

Now showing items 1-5 of 5

    • An Efficient Feathering System with Collision Control 

      Liu, Le; Li, Xiaosheng; Chen, Yanyun; Liu, Xuehui; Zhang, Jian J.; Wu, Enhua (The Eurographics Association and John Wiley & Sons Ltd., 2015)
      We present an efficient interactive system for dressing a naked bird with feathers. In our system, a skeleton associated with guide feathers is used to describe the distribution of the body feathers. The special skeleton ...

    • Guided Mesh Normal Filtering 

      Zhang, Wangyu; Deng, Bailin; Zhang, Juyong; Bouaziz, Sofien; Liu, Ligang (The Eurographics Association and John Wiley & Sons Ltd., 2015)
      The joint bilateral filter is a variant of the standard bilateral filter, where the range kernel is evaluated using a guidance signal instead of the original signal. It has been successfully applied to various image ...

    • Mesh Denoising using Extended ROF Model with L1 Fidelity 

      Wu, Xiaoqun; Zheng, Jianmin; Cai, Yiyu; Fu, Chi-Wing (The Eurographics Association and John Wiley & Sons Ltd., 2015)
      This paper presents a variational algorithm for feature-preserved mesh denoising. At the heart of the algorithm is a novel variational model composed of three components: fidelity, regularization and fairness, which are ...

    • Object Completion using k-Sparse Optimization 

      Mavridis, Pavlos; Sipiran, Ivan; Andreadis, Anthousis; Papaioannou, Georgios (The Eurographics Association and John Wiley & Sons Ltd., 2015)
      We present a new method for the completion of partial globally-symmetric 3D objects, based on the detection of partial and approximate symmetries in the incomplete input dataset. In our approach, symmetry detection is ...

    • Projective Feature Learning for 3D Shapes with Multi-View Depth Images 

      Xie, Zhige; Xu, Kai; Shan, Wen; Liu, Ligang; Xiong, Yueshan; Huang, Hui (The Eurographics Association and John Wiley & Sons Ltd., 2015)
      Feature learning for 3D shapes is challenging due to the lack of natural paramterization for 3D surface models. We adopt the multi-view depth image representation and propose Multi-View Deep Extreme Learning Machine (MVD-ELM) ...