SEG-MAT: 3D Shape Segmentation Using Medial Axis Transform

@article{Lin2020SEGMAT3S,
  title={SEG-MAT: 3D Shape Segmentation Using Medial Axis Transform},
  author={C. Y. Lin and Lingjie Liu and Changjian Li and Leif P. Kobbelt and Bin Wang and Shiqing Xin and Wenping Wang},
  journal={IEEE transactions on visualization and computer graphics},
  year={2020},
  volume={PP}
}
  • C. Lin, Lingjie Liu, +4 authors Wenping Wang
  • Published 20 October 2020
  • Computer Science, Medicine
  • IEEE transactions on visualization and computer graphics
Segmenting arbitrary 3D objects into constituent parts that are structurally meaningful is a fundamental problem encountered in a wide range of computer graphics applications. Existing methods for 3D shape segmentation suffer from complex geometry processing and heavy computation caused by using low-level features and fragmented segmentation results due to the lack of global consideration. We present an efficient method, called SEG-MAT, based on the medial axis transform (MAT) of the input… Expand
Unsupervised learning for cuboid shape abstraction via joint segmentation from point clouds
  • Kaizhi Yang, Xuejin Chen
  • Computer Science
  • ACM Trans. Graph.
  • 2021
TLDR
This paper proposes an unsupervised shape abstraction method to map a point cloud into a compact cuboid representation and designs four novel losses to jointly supervise the two branches in terms of geometric similarity and cuboid compactness. Expand
Coverage Axis: Inner Point Selection for 3D Shape Skeletonization
TLDR
Different from previous methods that rely on local approximation error, this method allows a global consideration of the overall shape structure, leading to an efficient high-level abstraction and superior robustness to noise. Expand
Point cloud decomposition by internal and external critical points
  • Jing Tang, Yinghui Wang, X. Ning, Ke Lv
  • Computers & Graphics
  • 2021
Point2Skeleton: Learning Skeletal Representations from Point Clouds
TLDR
This work introduces Point2Skeleton, an unsupervised method to learn skeletal representations from point clouds that uses the insights of the medial axis transform (MAT) to capture the intrinsic geometric and topological natures of the original input points. Expand
Unsupervised learning for cuboid shape abstraction via joint segmentation from point clouds
  • Kaizhi Yang, Xuejin Chen
  • 2021
Representing complex 3D objects as simple geometric primitives, known as shape abstraction, is important for geometric modeling, structural analysis, and shape synthesis. In this paper, we propose anExpand

References

SHOWING 1-10 OF 54 REFERENCES
Shape Segmentation by Approximate Convexity Analysis
TLDR
A shape segmentation method to directly optimize the decomposition based on a characterization of the expected geometry of a part in a shape, which yields results that are comparable to state-of-the-art techniques evaluated on complete shapes. Expand
Part-Based Segmentation by Skeleton Cut Space Analysis
We present a new method for part-based segmentation of voxel shapes that uses medial surfaces to define a segmenting cut at each medial voxel. The cut has several desirable properties – smoothness,Expand
Topology driven 3D mesh hierarchical segmentation
TLDR
This paper proposes to address the semantic- oriented 3D mesh hierarchical segmentation problem, using enhanced topological skeletons, and presents approach results, with low computation times, in robust and meaningful compatible hierarchical decompositions. Expand
A benchmark for 3D mesh segmentation
TLDR
The results suggest that people are remarkably consistent in the way that they segment most 3D surface meshes, that no one automatic segmentation algorithm is better than the others for all types of objects, and that algorithms based on non-local shape features seem to produce segmentations that most closely resemble ones made by humans. Expand
Directionally Convolutional Networks for 3D Shape Segmentation
TLDR
This paper proposes a novel 3D shape representation learning approach, Directionally Convolutional Network (DCN), which extends convolution operations from images to the surface mesh of 3D shapes and demonstrates that this approach outperforms the current state-of-the-arts on a large variety of3D shapes. Expand
Q-MAT
TLDR
An efficient method is presented that uses quadratic error minimization to compute a structurally simple, geometrically accurate, and compact representation of the medial axis transform, and produces a simple and accurate piecewise linear approximation of the MAT. Expand
Learning 3D mesh segmentation and labeling
This paper presents a data-driven approach to simultaneous segmentation and labeling of parts in 3D meshes. An objective function is formulated as a Conditional Random Field model, with termsExpand
Erosion thickness on medial axes of 3D shapes
TLDR
A global significance measure that generalizes in 3D the classical Erosion Thickness measure over the medial axes of 2D shapes and demonstrates the utility of ET in extracting clean, shape-revealing and topology-preserving skeletons of 3D shapes. Expand
Unsupervised 3D shape segmentation and co-segmentation via deep learning
TLDR
A novel unsupervised algorithm for automatically segmenting a single 3D shape or co-segmenting a family of 3D shapes using deep learning based on deep learning, which achieves better or comparable performance over the state-of-the-art methods. Expand
3D Mesh Segmentation Methodologies for CAD applications
D mesh segmentation is a fundamental process for Digital Shape Reconstruction in a variety of applications including Reverse Engineering, Medical Imaging, etc. It is used to provide a high levelExpand
...
1
2
3
4
5
...