{"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/csgan-cyclic-synthesized-generative","title":"CSGAN: Cyclic-Synthesized Generative Adversarial Networks for Image-to-Image Transformation","arxiv_id":"1901.03554","date":"2019-01-11","proceeding":null,"authors":["Kishan Babu Kancharagunta","Shiv Ram Dubey"],"abstract":"The primary motivation of Image-to-Image Transformation is to convert an\nimage of one domain to another domain. Most of the research has been focused on\nthe task of image transformation for a set of pre-defined domains. Very few\nworks are reported that actually developed a common framework for\nimage-to-image transformation for different domains. With the introduction of\nGenerative Adversarial Networks (GANs) as a general framework for the image\ngeneration problem, there is a tremendous growth in the area of image-to-image\ntransformation. Most of the research focuses over the suitable objective\nfunction for image-to-image transformation. In this paper, we propose a new\nCyclic-Synthesized Generative Adversarial Networks (CSGAN) for image-to-image\ntransformation. The proposed CSGAN uses a new objective function (loss) called\nCyclic-Synthesized Loss (CS) between the synthesized image of one domain and\ncycled image of another domain. The performance of the proposed CSGAN is\nevaluated on two benchmark image-to-image transformation datasets, including\nCUHK Face dataset and CMP Facades dataset. The results are computed using the\nwidely used evaluation metrics such as MSE, SSIM, PSNR, and LPIPS. The\nexperimental results of the proposed CSGAN approach are compared with the\nlatest state-of-the-art approaches such as GAN, Pix2Pix, DualGAN, CycleGAN and\nPS2GAN. The proposed CSGAN technique outperforms all the methods over CUHK\ndataset and exhibits the promising and comparable performance over Facades\ndataset in terms of both qualitative and quantitative measures. The code is\navailable at https://github.com/KishanKancharagunta/CSGAN.","url_abs":"http://arxiv.org/abs/1901.03554v1","url_pdf":"http://arxiv.org/pdf/1901.03554v1.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":"csgan-cyclic-synthesized-generative","repo_url":"https://github.com/KishanKancharagunta/CSGAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"csgan-cyclic-synthesized-generative","repo_url":"https://github.com/KishanKancharagunta/CDGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"ssim","task_name":"SSIM"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"cycle-consistency-loss","method_name":"Cycle Consistency Loss"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gan-least-squares-loss","method_name":"GAN Least Squares Loss"},{"method_slug":"instance-normalization","method_name":"Instance Normalization"},{"method_slug":"patchgan","method_name":"PatchGAN"},{"method_slug":"pix2pix","method_name":"Pix2Pix"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}