{"id":13936241,"url":"https://github.com/GV1028/videogan","last_synced_at":"2025-07-19T21:32:10.036Z","repository":{"id":89231261,"uuid":"123511109","full_name":"GV1028/videogan","owner":"GV1028","description":"Implementation of \"Generating Videos with Scene Dynamics\" in Tensorflow","archived":false,"fork":false,"pushed_at":"2018-03-13T05:04:20.000Z","size":749,"stargazers_count":77,"open_issues_count":8,"forks_count":20,"subscribers_count":3,"default_branch":"master","last_synced_at":"2024-11-27T04:30:49.941Z","etag":null,"topics":["generative-adversarial-network","tensorflow","video","video-generation","video-representation-learning"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/GV1028.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2018-03-02T00:59:51.000Z","updated_at":"2024-08-26T15:42:07.000Z","dependencies_parsed_at":"2023-06-14T12:30:39.977Z","dependency_job_id":null,"html_url":"https://github.com/GV1028/videogan","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/GV1028/videogan","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GV1028%2Fvideogan","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GV1028%2Fvideogan/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GV1028%2Fvideogan/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GV1028%2Fvideogan/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/GV1028","download_url":"https://codeload.github.com/GV1028/videogan/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GV1028%2Fvideogan/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266019657,"owners_count":23864916,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["generative-adversarial-network","tensorflow","video","video-generation","video-representation-learning"],"created_at":"2024-08-07T23:02:30.762Z","updated_at":"2025-07-19T21:32:05.026Z","avatar_url":"https://github.com/GV1028.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# Generating Videos with Scene Dynamics\n\n## Introduction\nThis repository contains an implementation of \"Generating Videos with Scene Dynamics\" in Tensorflow. The paper can be found here (http://carlvondrick.com/tinyvideo/paper.pdf). The model learns to generate a video by upsampling from some latent space, using adversarial training.\n\n## Requirements\nFor running this code and reproducing the results, you need the following packages. Python 2.7 has been used.\n\nPackages:\n* TensorFlow\n* NumPy\n* cv2\n* scikit-video\n* scikit-image\n\n\n## VideoGAN - Architecture and Working\nAttached below is the architecture used in the paper [paper](http://carlvondrick.com/tinyvideo/paper.pdf).\u003cbr /\u003e\n![Video_GAN](images/videogan.png)\n\n## Usage  \nPlace the videos inside a folder called \"trainvideos\".\u003cbr /\u003e\nRun main.py with the required values for each flag variable.\n\n## Results\nBelow are some of the results on the model trained on MPII Cooking Activities dataset.\u003cbr /\u003e\n\u003ctable\u003e\u003ctr\u003e\u003ctd\u003e\n\u003cstrong\u003eReal videos\u003c/strong\u003e\u003cbr\u003e\n\u003cimg src='images/true1.gif'\u003e\n\u003cimg src='images/true2.gif'\u003e\n\u003cimg src='images/true3.gif'\u003e\u003cbr\u003e\n\u003cimg src='images/true4.gif'\u003e\n\u003cimg src='images/true5.gif'\u003e\n\u003cimg src='images/true6.gif'\u003e\u003cbr\u003e\n\u003cimg src='images/true7.gif'\u003e\n\u003cimg src='images/true8.gif'\u003e\n\u003cimg src='images/true9.gif'\u003e\n\u003c/td\u003e\u003ctd\u003e\n\u003cstrong\u003eGenerated videos\u003c/strong\u003e\u003cbr\u003e\n\u003cimg src='images/gen1.gif'\u003e\n\u003cimg src='images/gen2.gif'\u003e\n\u003cimg src='images/gen3.gif'\u003e\u003cbr\u003e\n\u003cimg src='images/gen4.gif'\u003e\n\u003cimg src='images/gen5.gif'\u003e\n\u003cimg src='images/gen6.gif'\u003e\u003cbr\u003e\n\u003cimg src='images/gen7.gif'\u003e\n\u003cimg src='images/gen8.gif'\u003e\n\u003cimg src='images/gen9.gif'\u003e\n\u003c/td\u003e\u003c/tr\u003e\u003c/table\u003e\n\n## Acknowledgements\n* [Generating Videos With Scene Dynamics](http://carlvondrick.com/tinyvideo/paper.pdf) - Carl Vondrick et al.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FGV1028%2Fvideogan","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FGV1028%2Fvideogan","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FGV1028%2Fvideogan/lists"}