【ShapeWorks】4. 工作流的三板斧 - How to Analyze Your Shape Model?
| No. | Content |
|---|---|
| 1 | 【ShapeWorks】1. 软件介绍及安装 |
| 2 | 【ShapeWorks】2. 工作流的三板斧 - How to Groom Your Dataset? |
| 3 | 【ShapeWorks】3. 工作流的三板斧 - How to Optimize Your Shape Model? |
| 4 | 【ShapeWorks】4. 工作流的三板斧 - How to Analyze Your Shape Model? |
| 5 | 【ShapeWorks】5. 典型例子 Ellipsoid 的运行及解析 |
文章目录
- 1. Surface Correspondences
- 2. Running ShapeWorks Studio
-
- 1. Using XML Files
- 2. Using Spreadsheets
- 3. Surface Reconstruction
- 4. Statistical Analysis
- 5. Group Differences
- 6. Feature Maps
- Ref
1. Surface Correspondences
ShapeWorks includes a Qt and VTK-based graphical user interface (GUI), ShapeWorks Studio, that allows visualizing the optimized particle system (i.e., correspondence model) for each shape sample where particle coloring is used to reflect correspondence among shapes.
Particles’ coloring reflects surface correspondences across diffferent shape samples
You can also scroll through the dataset and zoom in and out to inspect fewer or more samples. ShapeWorks Studio keeps a consistent camera view across all shape samples to facilitate qualitative comparisons of different samples relative to each other.
Correspondence model inspectation by scrolling through the dataset and zooming in & out.
https://sci.utah.edu/~shapeworks/doc-resources/mp4s/studio_scroll.mp4
2. Running ShapeWorks Studio
When you open ShapeWorks Studio without a project, either from terminal or double-clicking on the application binary/exe file, the splash screen is displayed to enable you to load a recent project, oepn existing projects on your local machine, or create a new project.
ShapeWorks Studio splash screen
1. Using XML Files
2. Using Spreadsheets
3. Surface Reconstruction
For visualization purposes, the shape’s particle system is used to reconstruct its surface mesh using a template-deformation approach to establish an inter-sample dense surface correspondence given a sparse set of optimized particles. To avoid introducing bias dut to template choice, we use an unbiased framework for template mesh construction that entails:
- A generalized Procrustes alignment to define the mean particle system
- A nonlinear warping function built using the shape’s particle system and the mean one as control points.
- A mean distance transform (DT) computed by averaging warped sample-specific DT.
The template mesh will then be constructed by triangulating the isosurface of this mean DT. A warping function is constructed to deform the dense template mesh to the sample space using the sample’s and mean particle systems as control points to reconstruct a sample-specific surface mesh.
Particle-based surface reconstruction currently supported by ShapeWorks Studio
4. Statistical Analysis
Statistical analysis is performed using principal component analysis (PCA), where the mean and modes of shape variation are computed based on the optimized correspondence model. Animation is allowed to watch the shape morph at various standard deviations along a user-selected variation mode.
Animating the shape variation along with a principal component while passing through the mean shape
5. Group Differences
6. Feature Maps
Ref
- How to Analyze Your Shape Model?