{"id":19517473,"url":"https://github.com/cvg/emap","last_synced_at":"2025-04-13T05:13:18.087Z","repository":{"id":242043304,"uuid":"807394786","full_name":"cvg/EMAP","owner":"cvg","description":"[CVPR'24] 3D Neural Edge Reconstruction","archived":false,"fork":false,"pushed_at":"2024-09-09T17:49:03.000Z","size":5013,"stargazers_count":181,"open_issues_count":0,"forks_count":8,"subscribers_count":13,"default_branch":"main","last_synced_at":"2025-04-13T05:13:11.834Z","etag":null,"topics":["3d-reconstruction","curves","edges","lines","nerf","neural-fields","neural-implicit-representations"],"latest_commit_sha":null,"homepage":"https://neural-edge-map.github.io/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/cvg.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","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":"2024-05-29T02:51:27.000Z","updated_at":"2025-04-06T03:24:06.000Z","dependencies_parsed_at":"2024-11-18T01:47:01.406Z","dependency_job_id":null,"html_url":"https://github.com/cvg/EMAP","commit_stats":null,"previous_names":["cvg/emap"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cvg%2FEMAP","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cvg%2FEMAP/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cvg%2FEMAP/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cvg%2FEMAP/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/cvg","download_url":"https://codeload.github.com/cvg/EMAP/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248665746,"owners_count":21142123,"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":["3d-reconstruction","curves","edges","lines","nerf","neural-fields","neural-implicit-representations"],"created_at":"2024-11-11T00:03:48.256Z","updated_at":"2025-04-13T05:13:18.021Z","avatar_url":"https://github.com/cvg.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n  \u003ch1 align=\"center\"\u003e3D Neural Edge Reconstruction\u003c/h1\u003e\n  \u003cp align=\"center\"\u003e\n    \u003ca href=\"https://github.com/rayeeli/\"\u003e\u003cstrong\u003eLei Li\u003c/strong\u003e\u003c/a\u003e\n    ·\n    \u003ca href=\"https://pengsongyou.github.io/\"\u003e\u003cstrong\u003eSongyou Peng\u003c/strong\u003e\u003c/a\u003e\n    ·\n    \u003ca href=\"https://niujinshuchong.github.io/\"\u003e\u003cstrong\u003eZehao Yu\u003c/strong\u003e\u003c/a\u003e\n    ·\n    \u003ca href=\"http://b1ueber2y.me/\"\u003e\u003cstrong\u003eShaohui Liu\u003c/strong\u003e\u003c/a\u003e\n    ·\n    \u003ca href=\"https://rpautrat.github.io/\"\u003e\u003cstrong\u003eRémi Pautrat\u003c/strong\u003e\u003c/a\u003e\n    \u003cbr\u003e\n    \u003ca href=\"\"\u003e\u003cstrong\u003eXiaochuan Yin\u003c/strong\u003e\u003c/a\u003e\n    ·\n    \u003ca href=\"https://people.inf.ethz.ch/pomarc/\"\u003e\u003cstrong\u003eMarc Pollefeys\u003c/strong\u003e\u003c/a\u003e\n  \u003c/p\u003e\n  \u003ch2 align=\"center\"\u003eCVPR 2024\u003c/h2\u003e\n  \u003ch3 align=\"center\"\u003e\u003ca href=\"https://openaccess.thecvf.com/content/CVPR2024/papers/Li_3D_Neural_Edge_Reconstruction_CVPR_2024_paper.pdf\"\u003ePaper\u003c/a\u003e | \u003ca href=\"https://youtu.be/ONXfu2b4Nug\"\u003eVideo\u003c/a\u003e | \u003ca href=\"https://neural-edge-map.github.io/\"\u003eProject Page\u003c/a\u003e\u003c/h3\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\" style=\"display: flex; justify-content: center;\"\u003e\n  \u003cimg src=\"./media/replica.gif\" style=\"width: 80%;\" /\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\nEMAP enables 3D edge reconstruction from multi-view 2D edge maps.  \n\u003c/p\u003e\n\u003cbr\u003e\n\n## Installation\n\n```\ngit clone https://github.com/cvg/EMAP.git\ncd EMAP\n\nconda create -n emap python=3.8\nconda activate emap\n\nconda install pytorch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 pytorch-cuda=12.1 -c pytorch -c nvidia\npip install -r requirements.txt\n```\n\n## Datasets\nDownload datasets:\n```\npython scripts/download_data.py \n```\nThe data is organized as follows:\n\n```\n\u003cscan_id\u003e\n|-- meta_data.json      # camera parameters\n|-- color               # images for each view\n    |-- 0_colors.png\n    |-- 1_colors.png\n    ...\n|-- edge_DexiNed        # edge maps extracted from DexiNed\n    |-- 0_colors.png\n    |-- 1_colors.png\n    ...\n|-- edge_PidiNet        # edge maps extracted from PidiNet\n    |-- 0_colors.png\n    |-- 1_colors.png\n    ...\n```\n\n## Training and Edge Extraction\nTo train and extract edges on different datasets, use the following commands:\n\n#### ABC-NEF_Edge Dataset\n```\nbash scripts/run_ABC.bash\n```\n\n#### Replica_Edge Dataset\n```\nbash scripts/run_Replica.bash\n```\n\n#### DTU_Edge Dataset\n```\nbash scripts/run_DTU.bash\n```\n\n### Checkpoints\nWe have uploaded the model checkpoints on [Google Drive](https://drive.google.com/file/d/1kU87MqDv5IvwjCt8I8KecTlIok39fuws/view?usp=sharing). \n\n## Evaluation\nTo evaluate extracted edges on ABC-NEF_Edge dataset, use the following commands:\n\n#### ABC-NEF_Edge Dataset\n```\npython src/eval/eval_ABC.py\n```\n\n## Code Release Status\n- [x] Training Code\n- [x] Inference Code\n- [x] Evaluation Code\n- [ ] Custom Dataset Support\n\n## License\n\nShield: [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n\nThe majority of EMAP is licensed under a [MIT License](LICENSE.txt).\n\n## \u003ca name=\"CitingEMAP\"\u003e\u003c/a\u003eCiting EMAP\n\nIf you find the code useful, please consider the following BibTeX entry.\n\n```BibTeX\n@InProceedings{li2024neural,\n  title={3D Neural Edge Reconstruction},\n  author={Li, Lei and Peng, Songyou and Yu, Zehao and Liu, Shaohui and Pautrat, R{\\'e}mi and Yin, Xiaochuan and Pollefeys, Marc},\n  booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},\n  year={2024},\n}\n```\n\n## Contact\nIf you encounter any issues, you can also contact Lei through lllei.li0386@gmail.com.\n\n## Acknowledgement\n\nThis project is built upon [NeuralUDF](https://github.com/xxlong0/NeuralUDF), [NeuS](https://github.com/Totoro97/NeuS) and [MeshUDF](https://github.com/cvlab-epfl/MeshUDF). We use pretrained [DexiNed](https://github.com/xavysp/DexiNed) and [PidiNet](https://github.com/hellozhuo/pidinet) for edge map extraction. We thank all the authors for their great work and repos.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcvg%2Femap","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcvg%2Femap","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcvg%2Femap/lists"}