1 repo
Models trained to map images between domains without requiring corresponding training pairs.
Distinguishing note: Specific to unsupervised translation tasks, distinct from paired methods.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Unpaired Image Translation. Refine with filters or upvote what's useful.
This project is a deep learning framework designed for training and deploying image-to-image translation models. It serves as a research platform for experimenting with neural network architectures that transform visual content between distinct stylistic domains, supporting both paired and unpaired training data. The framework distinguishes itself through its support for cycle-consistency constraints, which allow for image translation between domains without requiring corresponding paired examples. It provides a structured pipeline that utilizes adversarial loss optimization, where generator
Transforms images between distinct visual domains without requiring corresponding training examples.