{"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/bubgan-bubble-generative-adversarial-networks","title":"BubGAN: Bubble Generative Adversarial Networks for Synthesizing Realistic Bubbly Flow Images","arxiv_id":"1809.02266","date":"2018-09-07","proceeding":null,"authors":["Yucheng Fu","Yang Liu"],"abstract":"Bubble segmentation and size detection algorithms have been developed in\nrecent years for their high efficiency and accuracy in measuring bubbly\ntwo-phase flows. In this work, we proposed an architecture called bubble\ngenerative adversarial networks (BubGAN) for the generation of realistic\nsynthetic images which could be further used as training or benchmarking data\nfor the development of advanced image processing algorithms. The BubGAN is\ntrained initially on a labeled bubble dataset consisting of ten thousand\nimages. By learning the distribution of these bubbles, the BubGAN can generate\nmore realistic bubbles compared to the conventional models used in the\nliterature. The trained BubGAN is conditioned on bubble feature parameters and\nhas full control of bubble properties in terms of aspect ratio, rotation angle,\ncircularity and edge ratio. A million bubble dataset is pre-generated using the\ntrained BubGAN. One can then assemble realistic bubbly flow images using this\ndataset and associated image processing tool. These images contain detailed\nbubble information, therefore do not require additional manual labeling. This\nis more useful compared with the conventional GAN which generates images\nwithout labeling information. The tool could be used to provide benchmarking\nand training data for existing image processing algorithms and to guide the\nfuture development of bubble detecting algorithms.","url_abs":"http://arxiv.org/abs/1809.02266v1","url_pdf":"http://arxiv.org/pdf/1809.02266v1.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":"bubgan-bubble-generative-adversarial-networks","repo_url":"https://github.com/ycfu/BubGAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}