{"id":18401706,"url":"https://github.com/borealisai/noise_flow","last_synced_at":"2025-04-07T07:31:43.525Z","repository":{"id":41746575,"uuid":"201541131","full_name":"BorealisAI/noise_flow","owner":"BorealisAI","description":"Noise Flow: Noise Modeling with Conditional Normalizing Flows","archived":false,"fork":false,"pushed_at":"2021-05-04T15:45:27.000Z","size":1938,"stargazers_count":141,"open_issues_count":6,"forks_count":20,"subscribers_count":6,"default_branch":"master","last_synced_at":"2024-04-18T03:18:37.155Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/BorealisAI.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}},"created_at":"2019-08-09T21:12:16.000Z","updated_at":"2024-02-20T05:56:32.000Z","dependencies_parsed_at":"2022-09-07T10:11:14.111Z","dependency_job_id":null,"html_url":"https://github.com/BorealisAI/noise_flow","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BorealisAI%2Fnoise_flow","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BorealisAI%2Fnoise_flow/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BorealisAI%2Fnoise_flow/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BorealisAI%2Fnoise_flow/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/BorealisAI","download_url":"https://codeload.github.com/BorealisAI/noise_flow/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":223274449,"owners_count":17118005,"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":"2024-11-06T02:39:42.164Z","updated_at":"2024-11-06T02:39:42.737Z","avatar_url":"https://github.com/BorealisAI.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"Noise Flow - A normalizing flows model for image noise modeling and synthesis\n===\n\nThis repository provides the codes for training and testing the Noise Flow model used for image noise modeling and \nsynthesis as described in the paper:\n\n[**Noise Flow: Noise Modeling with Conditional Normalizing Flows**](https://arxiv.org/pdf/1908.08453.pdf)\n\nIt also provides code for training and testing a CNN-based image denoiser (DnCNN) using Noise Flow as a noise generator, with comparison to other noise generation methods (i.e., AWGN and signal-dependent noise).\n  \n# Required libraries\n\nPython (works with 3.6)\n\nTensorFlow (works with 1.12.0)\n\nTensorFlow Probability (tested with 0.5.0)\n\n_Despite not tested, the code may work with library versions other than the specified._\n\n# Required dataset\n\n[Smartphone Image Denoising Dataset (SIDD)](https://www.eecs.yorku.ca/~kamel/sidd/)\n\nIt is recommended to use the medium-size SIDD for training Noise Flow:\n\n[SIDD_Medium_Raw](http://bit.ly/2kHT7Yr)\n\nThe code checks for and downloads `SIDD_Medium_Raw` if it does not exist. \n\n# Training/Testing/Sampling\n\nStart by running `job_noise_flow.sh`\n\nIt contains a set of examples for training different models (as described in the paper) and optionally perform testing and \nsampling concurrently.\n\n## Important parameters\n\n`--sidd_path`: path to the SIDD dataset\n\n`--arch`: the architecture of the noise flow model\n\n`--cam`: (optional) to use/sample data from a specific camera\n\n`--iso`: (optional) to use/sample data from a specific ISO level\n\nRefer to `job_noise_flow.sh` or `ArgParser.py` for details on the rest of parameters.\n   \n# Sampling only\n\nTo use the Noise Flow trained model for generating noise samples:\n\nStart by running `sample_noise_flow.py`\n\n# Application to image denoising with DnCNN\n\nStart by running `job_dncnn.sh` which contains examples for training DnCNN with synthetic noise from a Gaussian, signal-dependent, or Noise Flow model. \nAlso, it contains an example for training with real noise from the SIDD.\n\n# Paper\n\n[Abdelrahman Abdelhamed](https://www.eecs.yorku.ca/~kamel/), [Marcus A. Brubaker](https://www.eecs.yorku.ca/~mab/), and [Michael S. Brown](https://www.eecs.yorku.ca/~mbrown/). Noise Flow: Noise Modeling with Conditional Normalizing Flows. In _ICCV_, 2019.\n\n[PDF](https://arxiv.org/pdf/1908.08453.pdf)\n\n# Citation\n\nIf you use Noise Flow in your research, we kindly ask that you cite the paper as follows:\n\n    @inproceedings{abdelhamed2019noiseflow,\n      title={{Noise Flow: Noise Modeling with Conditional Normalizing Flows}},\n      author={Abdelhamed, Abdelrahman and Brubaker, Marcus A and Brown, Michael S},\n      booktitle={International Conference on Computer Vision (ICCV)},\n      year={2019}\n    }\n\n# License\n\nThis project is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International\nPublic License. The terms and conditions can be found in the LICENSE file.\n\n# Contact\n\n[Abdelrahman Abdelhamed](https://www.eecs.yorku.ca/~kamel/) ([kamel@eecs.yorku.ca](mailto:kamel@eecs.yorku.ca))\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fborealisai%2Fnoise_flow","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fborealisai%2Fnoise_flow","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fborealisai%2Fnoise_flow/lists"}