{"id":13535329,"url":"https://github.com/Yevkuzn/semodepth","last_synced_at":"2025-04-02T01:30:30.293Z","repository":{"id":201845031,"uuid":"130192543","full_name":"Yevkuzn/semodepth","owner":"Yevkuzn","description":"Semi-supervised monocular depth map prediction","archived":false,"fork":false,"pushed_at":"2018-08-05T23:58:26.000Z","size":31,"stargazers_count":72,"open_issues_count":1,"forks_count":14,"subscribers_count":4,"default_branch":"master","last_synced_at":"2024-11-02T23:32:47.357Z","etag":null,"topics":["deep-learning","depth-estimation","monocular-depth"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Yevkuzn.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":"2018-04-19T09:34:30.000Z","updated_at":"2024-03-30T15:16:02.000Z","dependencies_parsed_at":null,"dependency_job_id":"30dec7f9-06dd-49b5-b443-4197d2f7d17f","html_url":"https://github.com/Yevkuzn/semodepth","commit_stats":null,"previous_names":["yevkuzn/semodepth"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Yevkuzn%2Fsemodepth","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Yevkuzn%2Fsemodepth/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Yevkuzn%2Fsemodepth/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Yevkuzn%2Fsemodepth/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Yevkuzn","download_url":"https://codeload.github.com/Yevkuzn/semodepth/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246738372,"owners_count":20825774,"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":["deep-learning","depth-estimation","monocular-depth"],"created_at":"2024-08-01T08:00:53.825Z","updated_at":"2025-04-02T01:30:30.036Z","avatar_url":"https://github.com/Yevkuzn.png","language":"Python","funding_links":[],"categories":["2. Monocular Depth (Semi- / Un-Supervised)","2. 单目深度估计(半监督、无监督)"],"sub_categories":["2.1 Stereo Consistency"],"readme":"# Semi-Supervised Deep Learning for Monocular Depth Map Prediction\n\nThis repository contains code for the depth estimation system as described in\n**[Semi-Supervised Deep Learning for Monocular Depth Map Prediction, CVPR 2017](http://openaccess.thecvf.com/content_cvpr_2017/papers/Kuznietsov_Semi-Supervised_Deep_Learning_CVPR_2017_paper.pdf)**\n\nBy Yevhen Kuznietsov, Jörg Stückler, Bastian Leibe at Computer Vision Group, RWTH Aachen University\n\n## Presentation video\n\n\u003ca href=\"http://www.youtube.com/watch?feature=player_embedded\u0026v=KpJRSJx5yKs\n\" target=\"_blank\"\u003e\u003cimg src=\"http://img.youtube.com/vi/KpJRSJx5yKs/0.jpg\" \nalt=\"IMAGE ALT TEXT HERE\" width=\"426\" height=\"240\" border=\"10\" /\u003e\u003c/a\u003e\n\n## Prerequisite\n\nIn order to run the code, your setup has to meet the following requirements (tested versions in parentheses. Other versions might work as well):\n\n* Python (2.7.14)\n  * SciPy (1.0.0)\n* TensorFlow (1.4.0)\n  * CUDA (9.1.x)\n  * cuDNN (7.0.x)\n* GPU compatible with CUDAv9.1\n\n### Running the system\n1.  Download network model [here](https://www.vision.rwth-aachen.de/media/papers/best_model.tgz)\n2.  Create a file, containing input-output file paths in each line. The format to be used for each line is `input_path/input.png,output_path/output.mat`. Example can be found at [filenames.txt](filenames.txt)\n3.  Edit the [config file](/inference/config.py), set all the paths.\n4.  Run the system: `python %PROJ_DIR%/inference/produce_predictions.py` \n\n## Remarks\n\n* While the model may work with other datasets, this code is only supposed to be run with input resolution of [KITTI](http://www.cvlibs.net/datasets/kitti/) dataset\n\n* The code was tested with 6GB NVIDIA GeForce GTX 980 Ti. It should also be possible to run it with less GPU RAM. Running on CPU may require code modifications.\n\n* The metric depth map predictions, as well as the inputs and the generated depth ground truth for 'Eigen' test set are available [here](https://www.vision.rwth-aachen.de/publication/00150/)\n\nIf you have any issues or questions about the code, you can contact [me](mailto:YevKuzn@gmail.com) or [my alter ego](mailto:Yevhen.Kuznietsov@esat.kuleuven.be)\n\n## Citing\n\nIf you find the depth estimation model useful in your research, please consider citing:\n\n    @InProceedings{Kuznietsov_2017_CVPR,\n        author = {Kuznietsov, Yevhen and Stuckler, Jorg and Leibe, Bastian},\n        title = {Semi-Supervised Deep Learning for Monocular Depth Map Prediction},\n        booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},\n        month = {July},\n        year = {2017}\n    } \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FYevkuzn%2Fsemodepth","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FYevkuzn%2Fsemodepth","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FYevkuzn%2Fsemodepth/lists"}