{"id":13981062,"url":"https://github.com/CQFIO/PhotographicImageSynthesis","last_synced_at":"2025-07-21T21:31:07.530Z","repository":{"id":41207668,"uuid":"98670537","full_name":"CQFIO/PhotographicImageSynthesis","owner":"CQFIO","description":"Photographic Image Synthesis with Cascaded Refinement Networks","archived":false,"fork":false,"pushed_at":"2022-02-07T16:54:09.000Z","size":1802,"stargazers_count":1249,"open_issues_count":14,"forks_count":230,"subscribers_count":70,"default_branch":"master","last_synced_at":"2024-02-15T01:32:27.600Z","etag":null,"topics":["cascaded-refinement-networks","image-synthesis","tensorflow"],"latest_commit_sha":null,"homepage":"https://cqf.io/ImageSynthesis/","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/CQFIO.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}},"created_at":"2017-07-28T17:05:53.000Z","updated_at":"2024-02-14T23:29:17.000Z","dependencies_parsed_at":"2022-08-26T04:51:17.568Z","dependency_job_id":null,"html_url":"https://github.com/CQFIO/PhotographicImageSynthesis","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/CQFIO/PhotographicImageSynthesis","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CQFIO%2FPhotographicImageSynthesis","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CQFIO%2FPhotographicImageSynthesis/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CQFIO%2FPhotographicImageSynthesis/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CQFIO%2FPhotographicImageSynthesis/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CQFIO","download_url":"https://codeload.github.com/CQFIO/PhotographicImageSynthesis/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CQFIO%2FPhotographicImageSynthesis/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266381899,"owners_count":23920588,"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","status":"online","status_checked_at":"2025-07-21T11:47:31.412Z","response_time":64,"last_error":null,"robots_txt_status":null,"robots_txt_updated_at":null,"robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["cascaded-refinement-networks","image-synthesis","tensorflow"],"created_at":"2024-08-09T04:01:56.225Z","updated_at":"2025-07-21T21:31:07.136Z","avatar_url":"https://github.com/CQFIO.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Photographic Image Synthesis with Cascaded Refinement Networks\n\nThis is a Tensorflow implementation of cascaded refinement networks to synthesize photographic images from semantic layouts.\n\n\u003cimg src=\"http://cqf.io/ImageSynthesis/teaser.png\"/\u003e\n\n## Setup\n\n### Requirement\nRequired python libraries: Tensorflow (\u003e=1.0) + Scipy + Numpy + Pillow.\n\nTested in Ubuntu + Intel i7 CPU + Nvidia Titan X (Pascal) with Cuda (\u003e=8.0) and CuDNN (\u003e=5.0). CPU mode should also work with minor changes.\n\n### Quick Start (Testing)\n1. Clone this repository.\n2. Download the pretrained models from Google Drive by running \"python download_models.py\". It takes several minutes to download all the models.\n3. Run \"python demo_512p.py\" or \"python demo_1024p.py\" (requires large GPU memory) to synthesize images.\n4. The synthesized images are saved in \"result_512p/final\" or \"result_1024p/final\".\n\n### Training\nTo train a model at 256p resolution, please set \"is_training=True\" and change the file paths for training and test sets accordingly in \"demo_256p.py\". Then run \"demo_256p.py\".\n\nTo train a model at 512p resolution, we fine-tune the pretrained model at 256p using \"demo_512p.py\". Also change \"is_training=True\" and file paths accordingly.\n\nTo train a model at 1024p resolution, we fine-tune the pretrained model at 512p using \"demo_1024p.py\". Also change \"is_training=True\" and file paths accordingly.\n\n## Video\nhttps://youtu.be/0fhUJT21-bs\n\n## Citation\nIf you use our code for research, please cite our paper:\n\nQifeng Chen and Vladlen Koltun. Photographic Image Synthesis with Cascaded Refinement Networks. In ICCV 2017.\n\n## Amazon Turk Scripts\nThe scripts are put in the folder \"mturk_scripts\".\n\n## Todo List\n1. Add the code and models for the GTA dataset.\n\n## Question\nIf you have any question or request about the code and data, please email me at chenqifeng22@gmail.com. If you need the pretrained model on NYU, please send an email to me.\n\n## License\nMIT License\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FCQFIO%2FPhotographicImageSynthesis","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FCQFIO%2FPhotographicImageSynthesis","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FCQFIO%2FPhotographicImageSynthesis/lists"}