Skip to content

KryptixOne/Spherical-Data-Generation-For-3D-Meshes

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

30 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Spherical Data Generation for 3D Meshes

Overview

This project focuses on generating spherical representations of 3D meshes using data from ShapeNet and Acronym datasets. The method employs hemispherical radial ray-casting to transform the data into a structured spherical format.

Dataset Representation

The ShapeNet and Acronym datasets are used to create a baseline representation, as shown below:

To achieve this representation, a sphere is placed around each object, with rays cast from its surface to capture spatial and grasp-related information. Only a hemisphere is utilized for data creation.


Resulting Data Representation

The resulting dataset consists of a spherical projection of the 3D meshes, organized into different channels:

Channel 1: Spherical Depth Data

Captures depth values by measuring hit-distance between the enclosing hemisphere and the object.

Channel 2: Absolute Grasp Position Data

Maps absolute grasp positions to the nearest ray in the spherical coordinate system.

Channel 3: Orientation Theta Value

Represents the inclination angle to determine grasp orientation.

Channel 4: Orientation Phi Value

Encodes the azimuthal angle to determine grasp orientation.

Channel 5: Rotational Gamma Value

Captures rotation along the grasp axis.


Gaussian Mixture Model (GMM) Representations

A key goal of this dataset is to model grasp position and orientation using probability distributions. Gaussian Mixture Models (GMMs) are applied to create probabilistic representations.

Dense Raw Data

GMM Dense Data - Positional Representation

GMM Dense Data - 3D Representation

Sparse Data - Positional Representation

GMM Sparse Data - Positional Representation


Conclusion

This dataset provides a spherical representation of 3D objects and their grasps, which can be leveraged for grasp planning, robotic manipulation, and probabilistic modeling of grasp distributions. The Gaussian Mixture Model analysis further enhances grasp prediction by capturing underlying probabilistic distributions.


Citation

If you use this dataset in your research, please consider citing this work.


About

Data Generation: Data is a spherical projection of the 3-D meshes.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages