Megapixel Size Image Creation using Generative Adversarial Networks
Marco Marchesi

TL;DR
This paper presents an optimized DCGAN-based method capable of generating high-resolution, photorealistic images up to 1024x1024 pixels using limited training data, advancing GAN applications in visual media.
Contribution
The paper introduces an optimized DCGAN approach for high-resolution image synthesis with limited data, improving photorealism for visual media production.
Findings
Generated images reach 1024x1024 resolution.
High photorealism achieved with limited dataset.
Potential for use in computer graphics and visual effects.
Abstract
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGenerative Adversarial Networks and Image Synthesis · Advanced Image Processing Techniques · Computer Graphics and Visualization Techniques
MethodsTruncation Trick
