Now showing items 1-3 of 3

    • Generating 3D Faces using Multi-column Graph Convolutional Networks 

      Li, Kun; Liu, Jingying; Lai, Yu-Kun; Yang, Jingyu (The Eurographics Association and John Wiley & Sons Ltd., 2019)
      In this work, we introduce multi-column graph convolutional networks (MGCNs), a deep generative model for 3D mesh surfaces that effectively learns a non-linear facial representation. We perform spectral decomposition of ...
    • Shape and Pose Estimation for Closely Interacting Persons Using Multi-view Images 

      Li, Kun; Jiao, Nianhong; Liu, Yebin; Wang, Yangang; Yang, Jingyu (The Eurographics Association and John Wiley & Sons Ltd., 2018)
      Multi-person pose and shape estimation is very challenging, especially when the persons have close interactions. Existing methods only work well when people are well spaced out in the captured images. However, close ...
    • SHREC 2020 Track: Non-rigid Shape Correspondence of Physically-Based Deformations 

      Dyke, Roberto M.; Zhou, Feng; Lai, Yu-Kun; Rosin, Paul L.; Guo, Daoliang; Li, Kun; Marin, Riccardo; Yang, Jingyu (The Eurographics Association, 2020)
      Commonly, novel non-rigid shape correspondence techniques focus on particular matching challenges. This can lead to the potential trade-off of poorer performance in other scenarios. An ideal dataset would provide a granular ...