Marc Eder

This doesn't repair the bug necessarily. It just fixes the number of dimensions to be 3, as opposed to some arbitrary dimension D.

I haven't tested this with CUDA 10. There may be an issue with that. I've only tested with CUDA 9.0.

Hmmm. I'm don't think so. This code provides an efficient approximation to the Earth Mover's Distance, but does not solve the linear program directly. I haven't looked at SciPy's Wasserstein...

Sorry I misspoke. By normalization, I meant just center the distributions. I am not sure how to best match their implementation, but I would be interested if you find any....

Hi @manmeet3591, glad you like the paper! Can you be a little more specific about the format of your data? Is it truly like (lat, lon, value)? If so, what...

Tangent images are really nothing more than a resampling of the data to a new, lower distortion, format. If your data is already indexed by spherical coordinates (like an equirectangular...

So SIFT is actually is baked into the implementation of the the [visibile keypoints function in my spherical distortion](https://github.com/meder411/Spherical-Package/blob/master/ext_modules/src/cpp/triangle_mesh.cpp#L1051) library. (This more of a result of tight timing before the...

Take a look at [this TangentUVToSpherical function](https://github.com/meder411/openMVG/blob/develop/src/openMVG/spherical/tangent_images.cpp#L290) in my PR to OpenMVG. This shows how to convert the coordinates from tangent image pixels back to equirectangular image pixels. Similarly, take...

@Artcs1 Okay this was something that was bugging me for a while, so I just pushed a fixe. [Version 1.1 of my spherical-distortion repo](https://github.com/meder411/Spherical-Package/tree/v1.1.0) now includes [a function to convert...

Sorry about that. I had anticipated another researcher (the authors of the OmniSYNTHIA dataset) posting their code publicly to generate the dataset. They had shared the MATLAB code with me...