{"id":24957101,"url":"https://github.com/agarnung/image-deblurring-exploration","last_synced_at":"2026-02-16T09:05:04.609Z","repository":{"id":274798019,"uuid":"917906180","full_name":"agarnung/image-deblurring-exploration","owner":"agarnung","description":"An attempt to make my mobile phone's camera work","archived":false,"fork":false,"pushed_at":"2025-03-23T12:35:52.000Z","size":30978,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-23T13:33:22.608Z","etag":null,"topics":["deblurring","deconvolution","image-processing","investigation"],"latest_commit_sha":null,"homepage":"","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/agarnung.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,"publiccode":null,"codemeta":null}},"created_at":"2025-01-16T21:36:06.000Z","updated_at":"2025-03-23T12:35:55.000Z","dependencies_parsed_at":"2025-03-23T13:38:38.415Z","dependency_job_id":null,"html_url":"https://github.com/agarnung/image-deblurring-exploration","commit_stats":null,"previous_names":["agarnung/image-deblurring-exploration"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agarnung%2Fimage-deblurring-exploration","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agarnung%2Fimage-deblurring-exploration/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agarnung%2Fimage-deblurring-exploration/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agarnung%2Fimage-deblurring-exploration/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/agarnung","download_url":"https://codeload.github.com/agarnung/image-deblurring-exploration/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":249081975,"owners_count":21209789,"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":["deblurring","deconvolution","image-processing","investigation"],"created_at":"2025-02-03T06:54:33.831Z","updated_at":"2025-10-14T00:02:44.006Z","avatar_url":"https://github.com/agarnung.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# image-deblurring-exploration\nAn attempt to make my mobile phone's camera work. Inspired by practical uses of deblurring/deconvolution techniques.\n\n\u003cp style=\"font-size: 44px;\"\u003eThe exploration is documented in the \u003ca href=\"https://github.com/agarnung/image-deblurrer/blob/main/notebook/README.md\" style=\"font-size: 44px; font-weight: bold;\"\u003enotebook\u003c/a\u003e.\u003c/p\u003e\n\nMy mobile phone camera is broken (i.e.  ```📉 : (📷 ⊂ 📱) → ⛓️‍💥```); the lens is shattered (photo attached below). In this repository, I investigate how to work around this problem using variational techniques in image processing to restore photos taken with the damaged camera.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"./assets/crashed_lense.jpg\" alt=\"Crashed lense\" title=\"Crashed lense\" style=\"display: inline-block; width: 300px\" /\u003e,\n\u003c/p\u003e\n\nCurrently, these are my type of photos:\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"./assets/6.jpg\" alt=\"Blurry photo 6\" title=\"Blurry photo 6\" style=\"display: inline-block; width: 300px\" /\u003e...\n\u003c/p\u003e\n\n...How do I improve them?\n\n## Project Description\n\nThe main goal of this project is to investigate and apply deblurring/deconvolution methods to improve photos taken with a mobile camera that has suffered physical damage, specifically to the lens. The images captured by this camera are blurry due to the damage, and traditional focus correction methods cannot be used due to the lack of precise information about the Point Spread Function (PSF). To address this issue, we explore deblurring techniques, both with known PSF (non-blind deblurring) and without it (blind deblurring), using variational techniques and numerical methods.\n\n## Objective\n\nThe goal is to automatically and effectively restore images through deconvolution techniques. This involves:\n\n- **Recovering the PSF (Point Spread Function)** using deblurring methods.\n- **Performing the deconvolution** of the damaged images to produce clearer and sharper photos.\n- **Evaluating the quality of the restored images** by comparing them with a reference image taken with a working camera.\n\n## Project overview\n\n* The folder notebook contains the main investigation.\n* The folder code contain the code utilized.\n\n## Troubleshooting\nInstalling heavy Python libraries like torch or torchvision, one can run out of space in /tmp. The workaround is to specify your own temporary directory:\n```bash\npip._vendor.urllib3.exceptions.ProtocolError: (\"Connection broken: OSError(28, 'No space left on device')\", OSError(28, 'No space left on device'))\n(venv_datos) alejandro@pop-os:/media/alejandro/DATOS/venv_DATOS/src/dwdn$ TMPDIR=/media/alejandro/DATOS/pip_cache pip install torch torchvision\n```\n\n## TODO\n* Proper use of the Markdown rendering on GitHub; e.g. why LaTeX. HTML tables... seem to fail.\n* Train model with data augmentation\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fagarnung%2Fimage-deblurring-exploration","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fagarnung%2Fimage-deblurring-exploration","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fagarnung%2Fimage-deblurring-exploration/lists"}