{"id":21629391,"url":"https://github.com/khanovico/depthimage-single","last_synced_at":"2026-03-04T21:32:28.316Z","repository":{"id":246010269,"uuid":"818252991","full_name":"khanovico/depthimage-single","owner":"khanovico","description":"depth estimation from monocular camera","archived":false,"fork":false,"pushed_at":"2024-06-28T14:27:18.000Z","size":4305,"stargazers_count":4,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-11T14:12:48.362Z","etag":null,"topics":["deep-neural-network","depth-estimation","image-processing","image-segmentation"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/khanovico.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,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-06-21T12:36:06.000Z","updated_at":"2024-07-20T22:53:33.000Z","dependencies_parsed_at":"2024-06-28T15:51:38.645Z","dependency_job_id":null,"html_url":"https://github.com/khanovico/depthimage-single","commit_stats":null,"previous_names":["khanovict/depthimage-single","xleonsalman/depthimage-single","khanovico/depthimage-single"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/khanovico/depthimage-single","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/khanovico%2Fdepthimage-single","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/khanovico%2Fdepthimage-single/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/khanovico%2Fdepthimage-single/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/khanovico%2Fdepthimage-single/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/khanovico","download_url":"https://codeload.github.com/khanovico/depthimage-single/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/khanovico%2Fdepthimage-single/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30093806,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-04T20:42:30.420Z","status":"ssl_error","status_checked_at":"2026-03-04T20:42:30.057Z","response_time":59,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["deep-neural-network","depth-estimation","image-processing","image-segmentation"],"created_at":"2024-11-25T02:07:36.777Z","updated_at":"2026-03-04T21:32:28.286Z","avatar_url":"https://github.com/khanovico.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Depth Image from Single Camera\n\nMIT License\n\nA simple end-to-end model that achieves state-of-the-art performance in depth prediction implemented in PyTorch. We used a Feature Pyramid Network (FPN) backbone to estimate depth map from a single input RGB image. We tested the performance of our model on the NYU Depth V2 Dataset (Official Split) and the KITTI Dataset (Eigen Split).\n\n## Requirements\n\n* Python 3\n* Jupyter Notebook (for visualization)\n* PyTorch \n  * Tested with PyTorch 0.3.0.post4\n* CUDA 8 (if using CUDA)\n\n\n## To Run\n\n```\npython3 main_fpn.py --cuda --bs 6\n```\nTo continue training from a saved model, use\n```\npython3 main_fpn.py --cuda --bs 6 --r True --checkepoch 10\n```\nTo visualize the reconstructed data, run the jupyter notebook in vis.ipynb.\n\n## References\n* Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multiscale\ndeep network. In: Advances in neural information processing systems (NIPS). (2014)\n2366–2374\n* Geiger, Andreas, et al. \"Vision meets robotics: The KITTI dataset.\" The International Journal of Robotics Research 32.11 (2013): 1231-1237.\n* C. Godard, O. Mac Aodha, and G. J. Brostow. Unsupervised monocular depth estimation with left-right consistency. arXiv:1609.03677v2, 2016.\n* Hu, Junjie, et al. \"Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries.\" arXiv preprint arXiv:1803.08673 (2018).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkhanovico%2Fdepthimage-single","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkhanovico%2Fdepthimage-single","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkhanovico%2Fdepthimage-single/lists"}