Optimal Transport Python Packages

pot

POT : Python Optimal Transport

331K 3K 571

point-cloud-utils

An easy-to-use Python library for processing and manipulating 3D point clouds and meshes.

294K 2K 120

ott-jax

Optimal transport tools implemented with the JAX framework, to solve large scale matching problems of any flavor.

35K 764 139

torchcfm

TorchCFM: a Conditional Flow Matching library

11K 3K 226

torchdr

TorchDR - PyTorch Dimensionality Reduction

6K 216 15

torchebm

🍓 Simulation-free, GPU-first generative modeling in PyTorch ⚡ Composable primitives for scalable, stable training of modern EBMs, diffusion, flow matching, and Schrödinger bridges.

3K 115 25

otswap

Discrete optimal transport reconstruction of cosmological displacement fields and redshift-space distortion correction, for simulations and surveys. C++17 and Python

2K 0 0

moscot

Multi-omic single-cell optimal transport tools

1K 218 16

polystep

Training non-differentiable networks via optimal transport.

974 34 1

flash-sinkhorn

The official repository of FlashSinkhorn [ICML 2026 Oral]

913 223 22

fugw

Scalable python GPU solvers for fused unbalanced gromov-wasserstein optimal transport problems, with routines and examples to align brain data (fMRI)

820 53 6

pyapd

Computing (optimal) anisotropic power diagrams using GPU acceleration

550 17 2

wot

A software package for analyzing snapshots of developmental processes

516 166 38

wax-ot

WaX: explainable Wasserstein distances. Attributes a Wasserstein distance to instances, features and subspaces (Naumann, Kauffmann and Montavon, TPAMI 2026).

420 0 0

ggml-ot

Improve Optimal Transport applications by Global Ground Metric Learning (published at AISTATS2025). This package supports single-cell data in Anndata format and generic array-like data.

374 5 0

otretarget-pytorch

Implementation of OTRetarget: Joint Robot and Object Motion Retargeting via Optimal Transport

324 5 0

bioiot

Plug-and-play semi-relaxed inverse optimal transport (IOT) in Python: Anderson-accelerated soft Sinkhorn with exact implicit gradients, sklearn-style fitting, transition matrices, random-walk pseudotime, AnnData/scanpy interface, matplotlib plots. numpy in, numpy out.

288 0 0