3260 papers • 126 benchmarks • 313 datasets
Infinite Image Generation refers to the task of generating an unlimited number of images that belong to a specific distribution or category. It is a challenging task, as it requires the model to capture the underlying patterns and distributions in the data, and generate images that are diverse, yet still follow the same patterns. There are various techniques and algorithms that can be used to perform infinite image generation, including Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), and Convolutional Neural Networks (CNNs).
(Image credit: Papersgraph)
These leaderboards are used to track progress in image-generation
Use these libraries to find image-generation models and implementations
No subtasks available.
This work develops a method to generate infinite high-resolution images with diverse and complex content based on a perfectly equivariant patch-wise generator with synchronous interpolations in the image and latent spaces and modify the AdaIN mechanism to work in such a setup.
Adding a benchmark result helps the community track progress.