{"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/video-imagination-from-a-single-image-with","title":"Video Imagination from a Single Image with Transformation Generation","arxiv_id":"1706.04124","date":"2017-06-13","proceeding":null,"authors":["Baoyang Chen","Wenmin Wang","Jinzhuo Wang","Xiongtao Chen"],"abstract":"In this work, we focus on a challenging task: synthesizing multiple imaginary\nvideos given a single image. Major problems come from high dimensionality of\npixel space and the ambiguity of potential motions. To overcome those problems,\nwe propose a new framework that produce imaginary videos by transformation\ngeneration. The generated transformations are applied to the original image in\na novel volumetric merge network to reconstruct frames in imaginary video.\nThrough sampling different latent variables, our method can output different\nimaginary video samples. The framework is trained in an adversarial way with\nunsupervised learning. For evaluation, we propose a new assessment metric\n$RIQA$. In experiments, we test on 3 datasets varying from synthetic data to\nnatural scene. Our framework achieves promising performance in image quality\nassessment. The visual inspection indicates that it can successfully generate\ndiverse five-frame videos in acceptable perceptual quality.","url_abs":"http://arxiv.org/abs/1706.04124v2","url_pdf":"http://arxiv.org/pdf/1706.04124v2.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":"video-imagination-from-a-single-image-with","repo_url":"https://github.com/gitpub327/VideoImagination","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"image-quality-assessment","task_name":"Image Quality Assessment"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.04124","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}