Browsing by Author "Chen, Zhonggui"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Image Representation on Curved Optimal Triangulation
    (© 2022 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd., 2022) Xiao, Yanyang; Cao, Juan; Chen, Zhonggui; Hauser, Helwig and Alliez, Pierre
    Image triangulation aims to generate an optimal partition with triangular elements to represent the given image. One bottleneck in ensuring approximation quality between the original image and a piecewise approximation over the triangulation is the inaccurate alignment of straight edges to the curved features. In this paper, we propose a novel variational method called curved optimal triangulation, where not all edges are straight segments, but may also be quadratic Bézier curves. The energy function is defined as the total approximation error determined by vertex locations, connectivity and bending of edges. The gradient formulas of this function are derived explicitly in closed form to optimize the energy function efficiently. We test our method on several models to demonstrate its efficacy and ability in preserving features. We also explore its applications in the automatic generation of stylization and Lowpoly images. With the same number of vertices, our curved optimal triangulation method generates more accurate and visually pleasing results compared with previous methods that only use straight segments.
  • Thumbnail Image
    Item
    A Style Transfer Network of Local Geometry for 3D Mesh Stylization
    (The Eurographics Association, 2023) Kang, Hongyuan; Dong, Xiao; Guo, Xufei; Cao, Juan; Chen, Zhonggui; Chaine, Raphaëlle; Deng, Zhigang; Kim, Min H.
    Style transfer of images develops rapidly, however, only a few studies focus on geometric style transfer on 3D models. In this paper, we propose a style learning network to synthesize local geometric textures with similar styles on source mesh, driven by specific mesh or image features. Our network modifies a source mesh by predicting the displacement of vertices along the normal direction to generate geometric details. To constrain the style of the source mesh to be consistent with a specific style mesh, we define a style loss on 2D projected images of two meshes based on a differentiable renderer. We extract a set of global and local features from multiple views of 3D models via a pre-trained VGG network, driving the deformation of the source mesh based on the style loss. Our network is flexible in style learning as it can extract features from meshes and images to guide geometric deformation. Experiments verify the robustness of the proposed network and show the outperforming results of transferring multiple styles to the source mesh. We also conduct experiments to analyze the effectiveness of network design.
  • Thumbnail Image
    Item
    Superpixel Generation by Agglomerative Clustering With Quadratic Error Minimization
    (© 2019 The Eurographics Association and John Wiley & Sons Ltd., 2019) Dong, Xiao; Chen, Zhonggui; Yao, Junfeng; Guo, Xiaohu; Chen, Min and Benes, Bedrich
    Superpixel segmentation is a popular image pre‐processing technique in many computer vision applications. In this paper, we present a novel superpixel generation algorithm by agglomerative clustering with quadratic error minimization. We use a quadratic error metric (QEM) to measure the difference of spatial compactness and colour homogeneity between superpixels. Based on the quadratic function, we propose a bottom‐up greedy clustering algorithm to obtain higher quality superpixel segmentation. There are two steps in our algorithm: merging and swapping. First, we calculate the merging cost of two superpixels and iteratively merge the pair with the minimum cost until the termination condition is satisfied. Then, we optimize the boundary of superpixels by swapping pixels according to their swapping cost to improve the compactness. Due to the quadratic nature of the energy function, each of these atomic operations has only (1) time complexity. We compare the new method with other state‐of‐the‐art superpixel generation algorithms on two datasets, and our algorithm demonstrates superior performance.Superpixel segmentation is a popular image pre‐processing technique in many computer vision applications. In this paper, we present a novel superpixel generation algorithm by agglomerative clustering with quadratic error minimization. We use a quadratic error metric (QEM) to measure the difference of spatial compactness and colour homogeneity between superpixels. Based on the quadratic function, we propose a bottom‐up greedy clustering algorithm to obtain higher quality superpixel segmentation. There are two steps in our algorithm: merging and swapping. First, we calculate the merging cost of two superpixels and iteratively merge the pair with the minimum cost until the termination condition is satisfied. Then, we optimize the boundary of superpixels by swapping pixels according to their swapping cost to improve the compactness. Due to the quadratic nature of the energy function, each of these atomic operations has only O(1) time complexity. We compare the new method with other state‐of‐the‐art superpixel generation algorithms on two datasets, and our algorithm demonstrates superior performance.