{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/megapixel-size-image-creation-using","title":"Megapixel Size Image Creation using Generative Adversarial Networks","arxiv_id":"1706.00082","date":"2017-05-31","proceeding":null,"authors":["Marco Marchesi"],"abstract":"Since its appearance, Generative Adversarial Networks (GANs) have received a\nlot of interest in the AI community. In image generation several projects\nshowed how GANs are able to generate photorealistic images but the results so\nfar did not look adequate for the quality standard of visual media production\nindustry. We present an optimized image generation process based on a Deep\nConvolutional Generative Adversarial Networks (DCGANs), in order to create\nphotorealistic high-resolution images (up to 1024x1024 pixels). Furthermore,\nthe system was fed with a limited dataset of images, less than two thousand\nimages. All these results give more clue about future exploitation of GANs in\nComputer Graphics and Visual Effects.","url_abs":"http://arxiv.org/abs/1706.00082v1","url_pdf":"http://arxiv.org/pdf/1706.00082v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"truncation-trick","method_name":"Truncation Trick"}],"datasets_introduced":[],"methods_introduced":[{"slug":"truncation-trick","name":"Truncation Trick","full_name":"Truncation Trick"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.00082","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}