Yixin Zhuang yixin_Chinese

PostDoctoral Researcher

The Center on Frontiers of Computing Studies, Peking University

Email: yixin.zhuang at gmail.com


I am now a Boya PostDoctoral Researcher at Peking University, working with Prof. Baoquan Chen. I received my Ph.D degree in Computer Science in 2015 from National University of Defense Technology, China, under supervision of Prof. Yueshan Xiong. From 2012 Sep. to 2014 Sep., I studied at Washington University in St.Louis as a visiting student supervised by Prof. Tao Ju.

My primary research area is 3d shape analysis and modeling.



Surface remeshing with robust user-guided segmentation

Computational Visual Media 2018
Dawar Khan, Dong-Ming Yan, Fan Ding, Yixin Zhuang, Xiaopeng Zhang

Surface remeshing is widely required in modeling, animation, simulation, and many other computer graphics applications. Improving the elements’ quality is a challenging task in surface remeshing. Existing methods often fail to efficiently remove poor-quality elements especially in regions with sharp features. In this paper, we propose and use a robust segmentation method followed by remeshing the segmented mesh. Mesh segmentation is initiated using an existing Live-wire interaction approach and is further refined using local mesh operations. The refined segmented mesh is finally sent to the remeshing pipeline, in which each mesh segment is remeshed independently. An experimental study compares our mesh segmentation method as well as remeshing results with representative existing methods. We demonstrate that the proposed segmentation method is robust and suitable for remeshing.
| PDF |

Feature-Aligned Segmentation using Correlation Clustering

Computational Visual Media 2017 (best paper honorable mentioned)
Yixin Zhuang, Hang Dou, Nathan Carr, and Tao Ju

We present an algorithm for segmenting a mesh into patches whose boundaries are aligned with prominent ridge and valley lines of the shape. Our key insight is that this problem can be formulated as Correlation Clustering (CC), a graph partitioning problem originated from the data mining community. The formulation lends two unique advantages to our method over existing segmentation methods. First, since CC is non-parametric, our method requires few parameters to tune. Second, as CC is governed by edge weights in the graph, our method offers users direct and local control over the segmentation result. Our technical contributions include the construction of the weighted graph on which CC is defined, a speed-up strategy for computing CC on this graph, and an interactive tool for editing the segmentation. Our experiments showed that our method produces qualitatively better segmentations than existing methods on a wide range of inputs.
| Project | PDF |

Deformation-Driven Topology-Varying 3D Shape Correspondence

Siggraph Asia 2015, ACM Transaction on Graphics
Ibraheem Alhashim, Kai Xu, Yixin Zhuang, Junjie Cao, Patricio Simari, Hao Zhang

We present a deformation-driven approach to topology-varying 3D shape correspondence. In this paradigm, the best correspondence between two shapes is the one that results in a minimal-energy, possibly topology-varying, deformation that transforms one shape to conform to the other while respecting the correspondence. Our deformation model, called GeoTopo transform, allows both geometric and topological operations such as part split, duplication, and merging, leading to fine-grained and piecewise continuous correspondence results. The key ingredient of our correspondence scheme is a deformation energy that penalizes geometric distortion, encourages structure preservation, and simultaneously allows topology changes. This is accomplished by connecting shape parts using structural rods, which behave similarly to virtual springs but simultaneously allow the encoding of energies arising from geometric, structural, and topological shape variations. Driven by the combined deformation energy, an optimal shape correspondence is obtained via a pruned beam search. We demonstrate our deformation-driven correspondence scheme on extensive sets of man-made models with rich geometric and topological variation and compare the results to state-of-the-art approaches.
| PDF | Source code |

Anisotropic geodesics for live-wire mesh segmentation

Pacific Graphics 2014, Computer Graphics Forum
Yixin Zhuang, Ming Zou, Nathan Carr, Tao Ju

We present an interactive method for mesh segmentation that is inspired by the classical live-wire interaction for image segmentation. The core contribution of the work is the definition and computation of wires on surfaces that are likely to lie at segment boundaries. We define wires as geodesics in a new tensor-based anisotropic metric, which improves upon previous metrics in stability and feature-awareness. We further introduce a simple but effective mesh embedding approach that allows geodesic paths in an anisotropic path to be computed efficiently using existing algorithms designed for Euclidean geodesics. Our tool is particularly suited for delineating segmentation boundaries that are aligned with features or curvature directions, and we demonstrate its use in creating artist-guided segmentations.
| PDF | Supplemental | Demo+Data | Source Code |

A general and efficient method for finding cycles in 3D curve networks

SIGGRAPH Asia 2013, ACM Transactions on Graphics
Yixin Zhuang, Ming Zou, Nathan Carr, Tao Ju

Generating surfaces from 3D curve networks has been a longstanding problem in computer graphics. Recent attention to this area has resurfaced as a result of new sketch based modeling systems. In this work we present a new algorithm for finding cycles that bound surface patches. Unlike prior art in this area, the output of our technique is unrestricted, generating both manifold and non-manifold geometry with arbitrary genus. The novel insight behind our method is to formulate our problem as finding local mappings at the vertices and curves of our network, where each mapping describes how incident curves are grouped into cycles. This approach lends us the efficiency necessary to present our system in an interactive design modeler, whereby the user can adjust patch constraints and change the manifold properties of curves while the system automatically re-optimizes the solution.
| PDF | Supplemental | Demo+Data | Source Code |

Source code and tools development

1. Cycle discovery finds the right topology and geometry from 3D curve network. It firstly generates cycles from curve network, and then converts the cycles into triangular mesh. (source code and dependencies can be found on github.com/yixin26/Surfacing-of-Curves)
2. 3D Live-wire which is similar as 2D live-wire allows user to draw feature guided lines on the surface. The surface is finally segmented into patches by lines.
3. Mesh Segmentation tool creates a feature sensitive curve network on the surface. It has only a parameter to control the density of curves. The surface is partitioned as patches by the curves.
(2&3 are in the same project. Source code and dependencies can be found on github.com/yixin26/libs and github.com/yixin26/Mesh-Segmentation)
(Executable files and data can be found in project pages)