{"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/tgan-deep-tensor-generative-adversarial-nets","title":"TGAN: Deep Tensor Generative Adversarial Nets for Large Image Generation","arxiv_id":"1901.09953","date":"2019-01-28","proceeding":null,"authors":["Zihan Ding","Xiao-Yang Liu","Miao Yin","Linghe Kong"],"abstract":"Deep generative models have been successfully applied to many applications.\nHowever, existing works experience limitations when generating large images\n(the literature usually generates small images, e.g. 32 * 32 or 128 * 128). In\nthis paper, we propose a novel scheme, called deep tensor adversarial\ngenerative nets (TGAN), that generates large high-quality images by exploring\ntensor structures. Essentially, the adversarial process of TGAN takes place in\na tensor space. First, we impose tensor structures for concise image\nrepresentation, which is superior in capturing the pixel proximity information\nand the spatial patterns of elementary objects in images, over the\nvectorization preprocess in existing works. Secondly, we propose TGAN that\nintegrates deep convolutional generative adversarial networks and tensor\nsuper-resolution in a cascading manner, to generate high-quality images from\nrandom distributions. More specifically, we design a tensor super-resolution\nprocess that consists of tensor dictionary learning and tensor coefficients\nlearning. Finally, on three datasets, the proposed TGAN generates images with\nmore realistic textures, compared with state-of-the-art adversarial\nautoencoders. The size of the generated images is increased by over 8.5 times,\nnamely 374 * 374 in PASCAL2.","url_abs":"http://arxiv.org/abs/1901.09953v2","url_pdf":"http://arxiv.org/pdf/1901.09953v2.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":"tgan-deep-tensor-generative-adversarial-nets","repo_url":"https://github.com/hust512/Tensor-GAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"dictionary-learning","task_name":"Dictionary Learning"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.09953","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}