[RAL' 25 & IROS‘ 25] MapEval: Towards Unified, Robust and Efficient SLAM Map Evaluation Framework.

[ICRA@40] MS-Mapping: An Uncertainty-Aware Large-Scale Multi-Session LiDAR Mapping System

Official code for "A Normalized Gaussian Wasserstein Distance for Tiny Object Detection"

Optimal transport algorithms for Julia

PyTorch implementation of slicing adversarial network (SAN)

The Wasserstein Distance and Optimal Transport Map of Gaussian Processes

Measure the distance between two spectra/signals using optimal transport and related metrics

A materials discovery algorithm geared towards exploring high-performance candidates in new chemical spaces.

This Repository Contains Solution to the Assignments of the Generative Adversarial Networks (GANs) Specialization from deeplearning.ai on Coursera Taught by Sharon Zhou, Eda Zhou, Eric Zelikman

Source code for the ICML2019 paper "Subspace Robust Wasserstein Distances"

1D Wasserstein Statistical Loss in Pytorch

Functional Optimal Transport: Map Estimation and Domain Adaptation for Functional data

Discovering Conservation Laws using Optimal Transport and Manifold Learning

A thorough review of the paper "Learning Embeddings into Entropic Wasserstein Spaces" by Frogner et al. Includes a reproduction of the results on word embeddings.

Multi-Source Domain Adaptation via Optimal Transport for Student-Teacher Learning - UAI 2021

Header only C++ implementation of the Wasserstein distance (or earth mover's distance)

Persistence Diagrams in Julia

Unsupervised Domain Adaptation for Acoustic Scene Classification with Wasserstein Distance

LAMDA: Label Matching Deep Domain Adaptation - ICML 2021

Fast Topological Clustering with Wasserstein Distance (ICLR 2022)

My version of cWGAN-gp. Simply my cDCGAN-based but using the Wasserstein Loss and gradient penalty.

Sparse simplex projection-based Wasserstein k-means

Tools for quantitative analysis of nuclear magnetic resonance (NMR) spectra using the Wasserstein metric.

Lots of evaluation metrics for the generative adversarial networks in pytorch

Pytorch Implementation for Topic Modeling with Wasserstein Autoencoders

OT1D: Discrete Optimal Transport in 1D by Linear Programming

Topological Learning for Brain Networks (Annals of Applied Statistics; MICCAI 2021)

A collaborative mini-research project analyzing Wasserstein GANs (WGANs) through extensive literature review and experimental evaluation. Explores training stability, loss behavior, gradient penalties, and convergence characteristics, proposing insights to improve generative model robustness.

We've applied the Reptile algorithm to our GAN architectures. The peculiarity is the exclusion of G from meta-learning. Surprisingly, everything worked and the research was published in a paper. More details reported on the paper "Towards Latent Space Optimization of GANs Using Meta-Learning" and the thesis (Italian).

Neural Network Time Signal Detection with Wasserstein Loss