{"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/tempogan-a-temporally-coherent-volumetric-gan","title":"tempoGAN: A Temporally Coherent, Volumetric GAN for Super-resolution Fluid Flow","arxiv_id":"1801.09710","date":"2018-01-29","proceeding":null,"authors":["You Xie","Erik Franz","Mengyu Chu","Nils Thuerey"],"abstract":"We propose a temporally coherent generative model addressing the\nsuper-resolution problem for fluid flows. Our work represents a first approach\nto synthesize four-dimensional physics fields with neural networks. Based on a\nconditional generative adversarial network that is designed for the inference\nof three-dimensional volumetric data, our model generates consistent and\ndetailed results by using a novel temporal discriminator, in addition to the\ncommonly used spatial one. Our experiments show that the generator is able to\ninfer more realistic high-resolution details by using additional physical\nquantities, such as low-resolution velocities or vorticities. Besides\nimprovements in the training process and in the generated outputs, these inputs\noffer means for artistic control as well. We additionally employ a\nphysics-aware data augmentation step, which is crucial to avoid overfitting and\nto reduce memory requirements. In this way, our network learns to generate\nadvected quantities with highly detailed, realistic, and temporally coherent\nfeatures. Our method works instantaneously, using only a single time-step of\nlow-resolution fluid data. We demonstrate the abilities of our method using a\nvariety of complex inputs and applications in two and three dimensions.","url_abs":"http://arxiv.org/abs/1801.09710v2","url_pdf":"http://arxiv.org/pdf/1801.09710v2.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":"tempogan-a-temporally-coherent-volumetric-gan","repo_url":"https://github.com/thunil/tempoGAN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"tempogan-a-temporally-coherent-volumetric-gan","repo_url":"https://github.com/PaddlePaddle/PaddleScience/tree/develop/examples/tempoGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1801.09710","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}