renew curvature algorithms for mesh & pcl #1560
Open
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
[WIP] Start off by expressing my gratitude for the amazing pytorch3d library. However, while working with pytorch3d.ops.estimate_pointcloud_local_coord_frames function, I have noticed an issue with the description of the principal curvatures. More technically, the eigenvector corresponding to the minimal eigenvalue of covariance is exactly the normal vector, but neither the other two eigenvalues are principal curvatures. The current implementation does not accurately compute the curvature, which is a crucial metric in the field of 3D deep learning. Therefore, I have taken the liberty of developing codes for curvature algorithms based on pytorch3d for both meshes and point clouds. I believe that this algorithm would be a valuable addition to the library and would help fill the current gap in the available curvature computation methods.