Multi class one-shot image synthesis
1 papers with code • 0 benchmarks • 0 datasets
The goal of Multi-class one-shot image synthesis is to learn a generative model that can generate samples with visual attributes from as few as one or more images of at least 2 related classes.
Benchmarks
These leaderboards are used to track progress in Multi class one-shot image synthesis
No evaluation results yet. Help compare methods by
submitting
evaluation metrics.
Most implemented papers
DEff-GAN: Diverse Attribute Transfer for Few-Shot Image Synthesis
While single image methods can synthesize image samples with diversity, they do not model multiple images or capture the inherent relationship possible between two images.