ModelNet10

doi:doi:10.57702/q6jhri4k

ModelNet10

3D Convolutional Neural Networks are sensitive to transformations applied to their input. This is a problem because a voxelized version of a 3D object, and its rotated clone, will look unrelated to each other after passing through to the last layer of a network. Instead, an idealized model would preserve a meaningful representation of the voxelized object, while explaining the pose-difference between the two inputs.

BibTex:

@dataset{Zhiyang_Wang_and_Luana_Ruiz_and_Alejandro_Ribeiro_2024,
    abstract = {3D Convolutional Neural Networks are sensitive to transformations applied to their input. This is a problem because a voxelized version of a 3D object, and its rotated clone, will look unrelated to each other after passing through to the last layer of a network. Instead, an idealized model would preserve a meaningful representation of the voxelized object, while explaining the pose-difference between the two inputs.},
    author = {Zhiyang Wang and Luana Ruiz and Alejandro Ribeiro},
    doi = {10.57702/q6jhri4k},
    institution = {No Organization},
    keyword = {'3D Models', '3D Object Recognition', '3D models', '3D object recognition', 'CAD Models', 'Computer Vision', 'ModelNet10', 'Point clouds', 'Shape segmentation', 'Voxelized Data', 'computer vision', 'point cloud registration'},
    month = {dec},
    publisher = {TIB},
    title = {ModelNet10},
    url = {https://service.tib.eu/ldmservice/dataset/modelnet10},
    year = {2024}
}