{"id":13736613,"url":"https://github.com/omerbt/Splice","last_synced_at":"2025-05-08T12:33:21.241Z","repository":{"id":42054021,"uuid":"396380916","full_name":"omerbt/Splice","owner":"omerbt","description":"Official Pytorch Implementation for \"Splicing ViT Features for Semantic Appearance Transfer\" presenting \"Splice\" (CVPR 2022 Oral)","archived":false,"fork":false,"pushed_at":"2023-11-21T11:52:55.000Z","size":215567,"stargazers_count":372,"open_issues_count":4,"forks_count":32,"subscribers_count":10,"default_branch":"master","last_synced_at":"2024-11-09T14:46:40.149Z","etag":null,"topics":["cvpr2022","generative-models","image-translation","single-image","single-image-generation","splice","style-transfer","vision-transformer"],"latest_commit_sha":null,"homepage":"https://splice-vit.github.io/","language":"Jupyter Notebook","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/omerbt.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}},"created_at":"2021-08-15T14:38:23.000Z","updated_at":"2024-11-04T08:18:58.000Z","dependencies_parsed_at":"2023-02-17T23:16:09.438Z","dependency_job_id":"c7cff174-bae7-4948-bf88-3952d1ef4441","html_url":"https://github.com/omerbt/Splice","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/omerbt%2FSplice","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/omerbt%2FSplice/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/omerbt%2FSplice/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/omerbt%2FSplice/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/omerbt","download_url":"https://codeload.github.com/omerbt/Splice/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224732129,"owners_count":17360416,"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":["cvpr2022","generative-models","image-translation","single-image","single-image-generation","splice","style-transfer","vision-transformer"],"created_at":"2024-08-03T03:01:25.040Z","updated_at":"2025-05-08T12:33:21.228Z","avatar_url":"https://github.com/omerbt.png","language":"Jupyter Notebook","funding_links":[],"categories":["Jupyter Notebook"],"sub_categories":[],"readme":"# Splicing ViT Features for Semantic Appearance Transfer (CVPR 2022 - Oral)\n## [\u003ca href=\"https://splice-vit.github.io\" target=\"_blank\"\u003eProject Page\u003c/a\u003e]\n\n[![arXiv](https://img.shields.io/badge/arXiv-Splice-b31b1b.svg)](http://arxiv.org/abs/2201.00424)\n![Pytorch](https://img.shields.io/badge/PyTorch-\u003e=1.9.0-Red?logo=pytorch)\n[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/omerbt/Splice/blob/master/Splice.ipynb)\n![teaser](imgs/teaser.png)\n\n\n**Splice** is a method for semantic appearance transfer, as described in Splicing ViT Features for Semantic Appearance Transfer (\u003ca href=\"http://arxiv.org/abs/2201.00424\" target=\"_blank\"\u003elink to paper\u003c/a\u003e).\n\n\n\u003eGiven two input images—a source structure image and a target appearance image–our method generates a new image in which\nthe structure of the source image is preserved, while the visual appearance of the target image is transferred in a semantically aware manner.\nThat is, objects in the structure image are “painted” with the visual appearance of semantically related objects in the appearance image.\nOur method leverages a self-supervised, pre-trained ViT model as an external semantic prior. This allows us to train our generator only on\na single input image pair, without any additional information (e.g., segmentation/correspondences), and without adversarial training. Thus,\nour framework can work across a variety of objects and scenes, and can generate high quality results in high resolution (e.g., HD).\n\n\n## Getting Started\n### Installation\n\n```\ngit clone https://github.com/omerbt/Splice.git\npip install -r requirements.txt\n```\n\n\n### Run examples [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/omerbt/Splice/blob/master/Splice.ipynb)\n\n\nRun the following command to start training\n```bash\npython train.py --dataroot datasets/splicing/cows\n```\nIntermediate results will be saved to `\u003cdataroot\u003e/out/output.png` during optimization. The frequency of saving intermediate results is indicated in the `save_epoch_freq` flag of the configuration.\n\n## Sample Results\n![plot](imgs/results.png)\n\n## Citation\n```\n@inproceedings{tumanyan2022splicing,\n  title={Splicing ViT Features for Semantic Appearance Transfer},\n  author={Tumanyan, Narek and Bar-Tal, Omer and Bagon, Shai and Dekel, Tali},\n  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},\n  pages={10748--10757},\n  year={2022}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fomerbt%2FSplice","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fomerbt%2FSplice","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fomerbt%2FSplice/lists"}