{"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/learning-to-generate-time-lapse-videos-using","title":"Learning to Generate Time-Lapse Videos Using Multi-Stage Dynamic Generative Adversarial Networks","arxiv_id":"1709.07592","date":"2017-09-22","proceeding":"CVPR 2018 6","authors":["Wei Xiong","Wenhan Luo","Lin Ma","Wei Liu","Jiebo Luo"],"abstract":"Taking a photo outside, can we predict the immediate future, e.g., how would\nthe cloud move in the sky? We address this problem by presenting a generative\nadversarial network (GAN) based two-stage approach to generating realistic\ntime-lapse videos of high resolution. Given the first frame, our model learns\nto generate long-term future frames. The first stage generates videos of\nrealistic contents for each frame. The second stage refines the generated video\nfrom the first stage by enforcing it to be closer to real videos with regard to\nmotion dynamics. To further encourage vivid motion in the final generated\nvideo, Gram matrix is employed to model the motion more precisely. We build a\nlarge scale time-lapse dataset, and test our approach on this new dataset.\nUsing our model, we are able to generate realistic videos of up to $128\\times\n128$ resolution for 32 frames. Quantitative and qualitative experiment results\nhave demonstrated the superiority of our model over the state-of-the-art\nmodels.","url_abs":"http://arxiv.org/abs/1709.07592v3","url_pdf":"http://arxiv.org/pdf/1709.07592v3.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":"learning-to-generate-time-lapse-videos-using","repo_url":"https://github.com/CompVis/image2video-synthesis-using-cINNs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-to-generate-time-lapse-videos-using","repo_url":"https://github.com/weixiong-ur/mdgan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-to-generate-time-lapse-videos-using","repo_url":"https://github.com/zhangzjn/DTVNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":null,"task_name":"Generative Adversarial Network"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1709.07592","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}