Browsing by Author "Zhou, J."

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Feature‐Adaptive and Hierarchical Subdivision Gradient Meshes
    (© 2022 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd, 2022) Zhou, J.; Hettinga, G.J.; Houwink, S.; Kosinka, J.; Hauser, Helwig and Alliez, Pierre
    Gradient meshes, an advanced vector graphics primitive, are widely used by designers for creating scalable vector graphics. Traditional variants require a regular rectangular topology, which is a severe design restriction. The more advanced subdivision gradient mesh allows for an arbitrary manifold topology and is based on subdivision techniques to define the resulting colour surface. This also allows the artists to manipulate the geometry and colours at various levels of subdivision. Recent advances allow for the interpolation of both geometry and colour, local detail following edits at coarser subdivision levels and sharp colour transitions. A shortcoming of all existing methods is their dependence on global refinement, which makes them unsuitable for real‐time (commercial) design applications. We present a novel method that incorporates the idea of feature‐adaptive subdivision and uses approximating patches suitable for hardware tessellation with real‐time performance. Further novel features include multiple interaction mechanisms and self‐intersection prevention during interactive design/editing.
  • Thumbnail Image
    Item
    SiamesePointNet: A Siamese Point Network Architecture for Learning 3D Shape Descriptor
    (© 2020 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd, 2020) Zhou, J.; Wang, M. J.; Mao, W. D.; Gong, M. L.; Liu, X. P.; Benes, Bedrich and Hauser, Helwig
    We present a novel deep learning approach to extract point‐wise descriptors directly on 3D shapes by introducing Siamese Point Networks, which contain a global shape constraint module and a feature transformation operator. Such geometric descriptor can be used in a variety of shape analysis problems such as 3D shape dense correspondence, key point matching and shape‐to‐scan matching. The descriptor is produced by a hierarchical encoder–decoder architecture that is trained to map geometrically and semantically similar points close to one another in descriptor space. Benefiting from the additional shape contrastive constraint and the hierarchical local operator, the learned descriptor is highly aware of both the global context and local context. In addition, a feature transformation operation is introduced in the end of our networks to transform the point features to a compact descriptor space. The feature transformation can make the descriptors extracted by our networks unaffected by geometric differences in shapes. Finally, an N‐tuple loss is used to train all the point descriptors on a complete 3D shape simultaneously to obtain point‐wise descriptors. The proposed Siamese Point Networks are robust to many types of perturbations such as the Gaussian noise and partial scan. In addition, we demonstrate that our approach improves state‐of‐the‐art results on the BHCP benchmark.