ExtremalNeuralOptimalTransport and LightUnbalancedOptimalTransport
About ExtremalNeuralOptimalTransport
milenagazdieva/ExtremalNeuralOptimalTransport
PyTorch implementation of "Extremal Domain Translation with Neural Optimal Transport" (NeurIPS 2023)
This project helps image designers and researchers transform images from one style or domain to another, like turning a photo of a handbag into a shoe, or a real face into a comic face. You provide two sets of images representing different styles or domains, and it generates new images that translate the content of the first set into the style of the second. This tool is for anyone working with unpaired image-to-image translation, such as digital artists, game developers, or researchers exploring generative models.
About LightUnbalancedOptimalTransport
milenagazdieva/LightUnbalancedOptimalTransport
PyTorch implementation of "Light Unbalanced Optimal Transport" (NeurIPS 2024)
This project helps machine learning researchers and practitioners perform image-to-image translation when the source and target image collections have different numbers of items or contain irrelevant examples. It takes two sets of images, such as 'adult faces' and 'young faces,' and efficiently finds the optimal way to transform images from one set to match the style or characteristics of the other, even if categories like gender are imbalanced. The output is a mapping that allows you to translate an image from the source to the target domain while handling discrepancies in the input data.
Scores updated daily from GitHub, PyPI, and npm data. How scores work