{"id":19529279,"url":"https://github.com/isl-org/dfe","last_synced_at":"2025-04-26T11:34:37.614Z","repository":{"id":103593869,"uuid":"203639121","full_name":"isl-org/DFE","owner":"isl-org","description":null,"archived":false,"fork":false,"pushed_at":"2019-08-21T18:28:20.000Z","size":5824,"stargazers_count":45,"open_issues_count":1,"forks_count":15,"subscribers_count":10,"default_branch":"master","last_synced_at":"2023-10-20T20:27:22.920Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/isl-org.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2019-08-21T18:08:30.000Z","updated_at":"2023-09-18T12:29:57.000Z","dependencies_parsed_at":"2023-10-20T20:26:39.223Z","dependency_job_id":null,"html_url":"https://github.com/isl-org/DFE","commit_stats":null,"previous_names":[],"tags_count":0,"template":null,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/isl-org%2FDFE","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/isl-org%2FDFE/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/isl-org%2FDFE/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/isl-org%2FDFE/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/isl-org","download_url":"https://codeload.github.com/isl-org/DFE/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224033572,"owners_count":17244618,"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":[],"created_at":"2024-11-11T01:23:21.066Z","updated_at":"2024-11-11T01:23:22.639Z","avatar_url":"https://github.com/isl-org.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# DISCONTINUATION OF PROJECT #  \nThis project will no longer be maintained by Intel.  \nIntel has ceased development and contributions including, but not limited to, maintenance, bug fixes, new releases, or updates, to this project.  \nIntel no longer accepts patches to this project.  \n If you have an ongoing need to use this project, are interested in independently developing it, or would like to maintain patches for the open source software community, please create your own fork of this project.  \n  \n# Deep Fundamental Matrix Estimation\n\nThis repository contains code for training a network as described in our [paper](http://vladlen.info/papers/deep-fundamental.pdf):\n\n\u003eDeep Fundamental Matrix Estimation  \nRené Ranftl and Vladlen Koltun  \nEuropean Conference on Computer Vision (ECCV), 2018\n\nThe trained network can be used to compute a fundamental matrix based on noisy point correspondences.\n\n## Setup\n\n\nCreate and activate conda environment:\n\n```shell\nconda env create -f environment.yml\nconda activate dfe\n```\n\n## Train\n\nTraining can be performed with the following command:\n\n```shell\npython train.py --dataset [dataset folders]\n```\n\nDataset folders are assumed to be in COLMAP format. Multiple folders can be listed by separating them with a whitespace.\n\nAn example dataset can be found here: [Family](https://drive.google.com/open?id=1b4lb5La3dzn_D87sy-fpgCAbEnGRSLrL).\n\nTo get help:\n\n```shell\npython train.py -h\n```\n\n\n## Test\n\n```shell\npython test.py --dataset [dataset folders] --model [path to model]\n```\n\nA pre-trained model that was trained on Tanks and Temples can be found in the models folder.\n\n\n## Creating your own dataset\n\nThe dataloader assumes that a dataset folder contains the following files:\n\n```shell\nreconstruction.db \nsparse/0/cameras.bin\nsparse/0/images.bin\n\n```\n\n`cameras.bin` and `images.bin` are SfM reconstruction in COLMAP format. \n\n`reconstruction.db` contains descriptors, matches, etc.\n\nThese files are automatically created when performing reconstruction using COLMAP. We found that better results are achieved with less aggressive filtering for feature matching than the default COLMAP settings. The recommended way to create a training set is:\n\n1) Run COLMAP to produce `cameras.bin` and `images.bin` and initial `reconstruction.db`\n2) Run `get_features.sh` to produce a training set with higher outlier ratios to replace `reconstruction.db`\n\n## Citation\n\nPlease cite our paper if you use this code in your research:\n\n```bibtex\n@InProceedings{Ranftl2018,\n    author = {Ranftl, Rene and Koltun, Vladlen},\n    title = {Deep Fundamental Matrix Estimation},\n    booktitle = {The European Conference on Computer Vision (ECCV)},\n    year = {2018}\n}\n```\n\n## License\n\nMIT License\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fisl-org%2Fdfe","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fisl-org%2Fdfe","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fisl-org%2Fdfe/lists"}