{"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/lr-gan-layered-recursive-generative","title":"LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generation","arxiv_id":"1703.01560","date":"2017-03-05","proceeding":null,"authors":["Jianwei Yang","Anitha Kannan","Dhruv Batra","Devi Parikh"],"abstract":"We present LR-GAN: an adversarial image generation model which takes scene\nstructure and context into account. Unlike previous generative adversarial\nnetworks (GANs), the proposed GAN learns to generate image background and\nforegrounds separately and recursively, and stitch the foregrounds on the\nbackground in a contextually relevant manner to produce a complete natural\nimage. For each foreground, the model learns to generate its appearance, shape\nand pose. The whole model is unsupervised, and is trained in an end-to-end\nmanner with gradient descent methods. The experiments demonstrate that LR-GAN\ncan generate more natural images with objects that are more human recognizable\nthan DCGAN.","url_abs":"http://arxiv.org/abs/1703.01560v3","url_pdf":"http://arxiv.org/pdf/1703.01560v3.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":"lr-gan-layered-recursive-generative","repo_url":"https://github.com/jwyang/lr-gan.pytorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dcgan","method_name":"DCGAN"},{"method_slug":"relu","method_name":"ReLU"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/conditional-image-generation-on-cifar-10","task":"Conditional Image Generation","dataset":"CIFAR-10","model":"LR-GAN","rank_in_archive_order":22,"of":25,"metrics":{"Inception score":"7.17"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-cub-128-x-128","task":"Image Generation","dataset":"CUB 128 x 128","model":"LR-GAN","rank_in_archive_order":4,"of":4,"metrics":{"FID":"34.91","Inception score":"13.50"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-stanford-cars","task":"Image Generation","dataset":"Stanford Cars","model":"LR-GAN","rank_in_archive_order":4,"of":4,"metrics":{"FID":"88.80","Inception score":"5.25"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-stanford-dogs","task":"Image Generation","dataset":"Stanford Dogs","model":"LR-GAN","rank_in_archive_order":4,"of":4,"metrics":{"FID":"54.91","Inception score":"10.22"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1703.01560","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}