Megapixel Size Image Creation using Generative Adversarial Networks
This addresses the need for high-quality image generation in the visual media production industry, though it appears incremental.
The paper tackled generating photorealistic high-resolution images up to 1024x1024 pixels using an optimized DCGAN process, achieving results with a limited dataset of less than 2,000 images.
Since its appearance, Generative Adversarial Networks (GANs) have received a lot of interest in the AI community. In image generation several projects showed how GANs are able to generate photorealistic images but the results so far did not look adequate for the quality standard of visual media production industry. We present an optimized image generation process based on a Deep Convolutional Generative Adversarial Networks (DCGANs), in order to create photorealistic high-resolution images (up to 1024x1024 pixels). Furthermore, the system was fed with a limited dataset of images, less than two thousand images. All these results give more clue about future exploitation of GANs in Computer Graphics and Visual Effects.