bingham-rotation-learning
bingham-rotation-learning copied to clipboard
utiasSTARS
A Smooth Representation of SO(3) for Deep Rotation Learning with Uncertainty.
Very interesting work! Given A_vec, using your work we can represent quaternions, but how about vice verse? Given quaternions, can we get A_vec?
recently reading your paper, can you provide the media dataset, or a download link to the dataset
Hi! When I input a tensor of shape Bx4x4 into torch.symeig(A, eigenvectors=True), I get the following error: RuntimeError: Assertion `src->dim() == 2' failed. at /pytorch/aten/src/THC/generic/THCTensorMathMagma.cu:42 I am using torch version...
`unsqueeze` function will throw an exception if called without an argument. Now adds the missing argument
Metadata
Owner
Metadata
A Smooth Representation of SO(3) for Deep Rotation Learning with Uncertainty.