{"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/auto-embedding-generative-adversarial","title":"Auto-Embedding Generative Adversarial Networks for High Resolution Image Synthesis","arxiv_id":"1903.11250","date":"2019-03-27","proceeding":null,"authors":["Yong Guo","Qi Chen","Jian Chen","Qingyao Wu","Qinfeng Shi","Mingkui Tan"],"abstract":"Generating images via the generative adversarial network (GAN) has attracted\nmuch attention recently. However, most of the existing GAN-based methods can\nonly produce low-resolution images of limited quality. Directly generating\nhigh-resolution images using GANs is nontrivial, and often produces problematic\nimages with incomplete objects. To address this issue, we develop a novel GAN\ncalled Auto-Embedding Generative Adversarial Network (AEGAN), which\nsimultaneously encodes the global structure features and captures the\nfine-grained details. In our network, we use an autoencoder to learn the\nintrinsic high-level structure of real images and design a novel denoiser\nnetwork to provide photo-realistic details for the generated images. In the\nexperiments, we are able to produce 512x512 images of promising quality\ndirectly from the input noise. The resultant images exhibit better perceptual\nphoto-realism, i.e., with sharper structure and richer details, than other\nbaselines on several datasets, including Oxford-102 Flowers, Caltech-UCSD Birds\n(CUB), High-Quality Large-scale CelebFaces Attributes (CelebA-HQ), Large-scale\nScene Understanding (LSUN) and ImageNet.","url_abs":"http://arxiv.org/abs/1903.11250v2","url_pdf":"http://arxiv.org/pdf/1903.11250v2.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":[{"paper_slug":"auto-embedding-generative-adversarial","repo_url":"https://github.com/guoyongcs/AEGAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.11250","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}