Download
CycleGAN — in its original form — is a landmark in deep learning for image-to-image translation without paired data. Rather than requiring matching image pairs between source and target domains (which are often hard or impossible to obtain), CycleGAN learns two mappings — one from domain A to B, and another back from B to A — along with a cycle-consistency loss that encourages the round-trip to reconstruct the original image. This innovation lets the model learn domain-to-domain translations like turning horses into zebras, changing seasons, or transforming photos into paintings, using only collections of images from each domain. The original implementation (in Torch) has since been complemented by other re-implementations (including in PyTorch), but the core idea remains: unpaired image-to-image translation. Because of its flexibility, CycleGAN has become one of the most widely adopted generative models for domain translation tasks.
Features
- Performs unpaired image-to-image translation between two domains
- Learns bidirectional mappings (A→B and B→A) with cycle-consistency constraints
- Applicable to style transfer, domain adaptation, seasonal changes, photo-to-art, etc.
- Does not require matched image pairs — only separate domain datasets
- Works with generic images — no special pre-processing or labeling needed
- Produces visually coherent and realistic transformations even without explicit supervision
Project Samples
