{"id":20377584,"url":"https://github.com/reshalfahsi/zero-reference-low-light-image-enhancement","last_synced_at":"2026-04-18T14:04:21.885Z","repository":{"id":182923020,"uuid":"669328121","full_name":"reshalfahsi/zero-reference-low-light-image-enhancement","owner":"reshalfahsi","description":"Zero-Reference Low-Light Image Enhanchement","archived":false,"fork":false,"pushed_at":"2023-07-31T15:40:28.000Z","size":10794,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-08-25T18:58:18.924Z","etag":null,"topics":["image-enhancement","image-processing","low-light-image-enhancement","pytorch","pytorch-lightning","zero-dce"],"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/reshalfahsi.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}},"created_at":"2023-07-22T00:03:37.000Z","updated_at":"2024-06-27T23:49:06.000Z","dependencies_parsed_at":null,"dependency_job_id":"ef2d1e4d-ac4a-4127-b24f-655e9ba98680","html_url":"https://github.com/reshalfahsi/zero-reference-low-light-image-enhancement","commit_stats":null,"previous_names":["reshalfahsi/zero-reference-low-light-image-enhanchement","reshalfahsi/zero-reference-low-light-image-enhancement"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/reshalfahsi/zero-reference-low-light-image-enhancement","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reshalfahsi%2Fzero-reference-low-light-image-enhancement","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reshalfahsi%2Fzero-reference-low-light-image-enhancement/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reshalfahsi%2Fzero-reference-low-light-image-enhancement/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reshalfahsi%2Fzero-reference-low-light-image-enhancement/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/reshalfahsi","download_url":"https://codeload.github.com/reshalfahsi/zero-reference-low-light-image-enhancement/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reshalfahsi%2Fzero-reference-low-light-image-enhancement/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31971497,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-18T00:39:45.007Z","status":"online","status_checked_at":"2026-04-18T02:00:07.018Z","response_time":103,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["image-enhancement","image-processing","low-light-image-enhancement","pytorch","pytorch-lightning","zero-dce"],"created_at":"2024-11-15T01:45:40.358Z","updated_at":"2026-04-18T14:04:16.875Z","avatar_url":"https://github.com/reshalfahsi.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Zero-Reference Low-Light Image Enhancement\n\n\n \u003cdiv align=\"center\"\u003e\n    \u003ca href=\"https://colab.research.google.com/github/reshalfahsi/zero-reference-low-light-image-enhancement/blob/master/Zero_Reference_Low_Light_Image_Enhancement.ipynb\"\u003e\u003cimg src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"colab\"\u003e\u003c/a\u003e\n    \u003cbr /\u003e\n \u003c/div\u003e\n\nLow-light image enhancement aims to raise the quality of pictures taken in dim lighting, resulting in a brighter, clearer, and more visually appealing image without adding too much noise or distortion. One of the state-of-the-art methods for this computer vision task is Zero-DCE. This method uses just a low-light image without any image reference to learn how to produce an image with higher brightness. There are four loss functions crafted specifically for this zero-reference low-light image enhancement method, i.e., color constancy loss, exposure loss, illumination smoothness loss, and spatial consistency loss.\n\n\n## Experiment\n\n\nOpen the following [link](https://github.com/reshalfahsi/zero-reference-low-light-image-enhancement/blob/master/Zero_Reference_Low_Light_Image_Enhancement.ipynb) and hit the run all in the colab notebook to examine the overall processes.\n\n\n## Result\n\n## Quantitative Result\n\nThe quantitative performance of the model is exhibited in the table below.\n\nMetrics | Test Dataset |\n------------ | ------------- |\nColor Constancy Loss |  0.065 |\nExposure Loss | 0.391 |\nIllumination Smoothness Loss | 0.094 |\nSpatial Consistency Loss | 0.042 |\nTotal Loss | 0.592 |\nPSNR | 13.646 |\nSSIM | 0.663 |\nMAE | 0.170 |\n\n\n## Evaluation Metrics Curve\n\n\u003cp align=\"center\"\u003e \u003cimg src=\"https://github.com/reshalfahsi/zero-reference-low-light-image-enhancement/blob/master/assets/colorconstancy_loss_curve.png\" alt=\"colorconstancy_loss_curve\" \u003e \u003cbr /\u003e Color constancy loss curve on the train set and the validation set. \u003c/p\u003e\n\n\u003cp align=\"center\"\u003e \u003cimg src=\"https://github.com/reshalfahsi/zero-reference-low-light-image-enhancement/blob/master/assets/exposure_loss_curve.png\" alt=\"exposure_loss_curve\" \u003e \u003cbr /\u003e Exposure loss curve on the train set and the validation set. \u003c/p\u003e\n\n\u003cp align=\"center\"\u003e \u003cimg src=\"https://github.com/reshalfahsi/zero-reference-low-light-image-enhancement/blob/master/assets/illumination_smoothness_loss_curve.png\" alt=\"illumination_smoothness_loss_curve\" \u003e \u003cbr /\u003e Illumination smoothness loss curve on the train set and the validation set. \u003c/p\u003e\n\n\u003cp align=\"center\"\u003e \u003cimg src=\"https://github.com/reshalfahsi/zero-reference-low-light-image-enhancement/blob/master/assets/spatialconsistency_loss_curve.png\" alt=\"spatialconsistency_loss_curve\" \u003e \u003cbr /\u003e Spatial consistency loss curve on the train set and the validation set. \u003c/p\u003e\n\n\u003cp align=\"center\"\u003e \u003cimg src=\"https://github.com/reshalfahsi/zero-reference-low-light-image-enhancement/blob/master/assets/totalloss_curve.png\" alt=\"totalloss_curve\" \u003e \u003cbr /\u003e Total loss curve on the train set and the validation set. \u003c/p\u003e\n\n\u003cp align=\"center\"\u003e \u003cimg src=\"https://github.com/reshalfahsi/zero-reference-low-light-image-enhancement/blob/master/assets/psnr_curve.png\" alt=\"psnr_curve\" \u003e \u003cbr /\u003e PSNR curve on the train set and the validation set. \u003c/p\u003e\n\n\u003cp align=\"center\"\u003e \u003cimg src=\"https://github.com/reshalfahsi/zero-reference-low-light-image-enhancement/blob/master/assets/ssim_curve.png\" alt=\"ssim_curve\" \u003e \u003cbr /\u003e SSIM curve on the train set and the validation set. \u003c/p\u003e\n\n\u003cp align=\"center\"\u003e \u003cimg src=\"https://github.com/reshalfahsi/zero-reference-low-light-image-enhancement/blob/master/assets/mae_curve.png\" alt=\"mae_curve\" \u003e \u003cbr /\u003e MAE curve on the train set and the validation set. \u003c/p\u003e\n\n\n## Qualitative Result\n\nHere are some samples of the qualitative results of the model.\n\n\u003cp align=\"center\"\u003e \u003cimg src=\"https://github.com/reshalfahsi/zero-reference-low-light-image-enhancement/blob/master/assets/enhancement_qualitative_00.png\" alt=\"enhancement_qualitative_00\" \u003e \u003cbr /\u003e \u003cimg src=\"https://github.com/reshalfahsi/zero-reference-low-light-image-enhancement/blob/master/assets/enhancement_qualitative_01.png\" alt=\"enhancement_qualitative_01\" \u003e \u003cbr /\u003e \u003cimg src=\"https://github.com/reshalfahsi/zero-reference-low-light-image-enhancement/blob/master/assets/enhancement_qualitative_02.png\" alt=\"enhancement_qualitative_02\" \u003e \u003cbr /\u003e The qualitative results of the image enhancement method (comparing the original, the ground-truth, the PIL autocontrast, and the prediction). \u003c/p\u003e\n\n\n## Credit\n\n- [(Tutorial) Zero-DCE for low-light image enhancement](https://keras.io/examples/vision/zero_dce/)\n- [(Paper) Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://arxiv.org/pdf/2001.06826.pdf)\n- [PyTorch Lightning](https://lightning.ai/docs/pytorch/latest/)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Freshalfahsi%2Fzero-reference-low-light-image-enhancement","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Freshalfahsi%2Fzero-reference-low-light-image-enhancement","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Freshalfahsi%2Fzero-reference-low-light-image-enhancement/lists"}