A serverless client for reading and writing Neuroglancer Precomputed volumes both locally and on cloud services.
Unofficial packaging of the compresso algorithm based on work by Matejek et al.
Connected components on 3D images, supports multiple labels.
Skeletonize densely labeled image volumes.
Multithreaded cloud queue client.
Remap, mask, renumber, and in-place transpose numpy arrays.
Implementation of Dijkstra's Shortest Path algorithm on 3D images.
Multilabel marching cubes and simplification of volumetric data.
Numpy wrapper for fpzip algorithm (P. Lindstrom & M. Isenburg, 2006)
Image pyramid generation specialized for connectomics data types and procedures.
Multi-Label Anisotropic Euclidean Distance Transform 3D
Neuroglancer compressed_segmentation codec.