StrokeCoder: Path-Based Image Generation from Single Examples using Transformers
This addresses the challenge of limited training data for image generation, though it appears incremental as it applies existing Transformers to a specific path-based image task.
The paper tackles the problem of generating diverse images from a single path-based example by using a Transformer neural network to learn a generative model, producing a large set of deviated images that retain the original style and concept.
This paper demonstrates how a Transformer Neural Network can be used to learn a Generative Model from a single path-based example image. We further show how a data set can be generated from the example image and how the model can be used to generate a large set of deviated images, which still represent the original image's style and concept.