{"id":21028808,"url":"https://github.com/tuvovan/anl-hdri","last_synced_at":"2025-07-08T00:07:50.470Z","repository":{"id":166767796,"uuid":"296626609","full_name":"tuvovan/ANL-HDRI","owner":"tuvovan","description":"High Dynamic Range Image Synthesis via Attention Non-Local Network","archived":false,"fork":false,"pushed_at":"2021-06-13T05:25:36.000Z","size":3387,"stargazers_count":7,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-03-26T07:23:13.774Z","etag":null,"topics":["attention-network","convolutional-autoencoder","convolutional-neural-networks","hdr-image","hdr-imaging"],"latest_commit_sha":null,"homepage":"","language":"Python","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/tuvovan.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":"2020-09-18T13:18:48.000Z","updated_at":"2024-03-08T18:50:01.000Z","dependencies_parsed_at":"2023-07-29T12:45:21.111Z","dependency_job_id":null,"html_url":"https://github.com/tuvovan/ANL-HDRI","commit_stats":null,"previous_names":["tuvovan/anl-hdri"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tuvovan%2FANL-HDRI","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tuvovan%2FANL-HDRI/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tuvovan%2FANL-HDRI/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tuvovan%2FANL-HDRI/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tuvovan","download_url":"https://codeload.github.com/tuvovan/ANL-HDRI/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248570361,"owners_count":21126416,"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":["attention-network","convolutional-autoencoder","convolutional-neural-networks","hdr-image","hdr-imaging"],"created_at":"2024-11-19T11:59:11.209Z","updated_at":"2025-04-12T12:44:59.218Z","avatar_url":"https://github.com/tuvovan.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ANLHDR Imaging\nHigh Dynamic Range Image Synthesis via Attention Non-Local Network\n![teaser](teaser/HDRI.png)\n## Content\n- [ANL-HDRI](#anl-hdri)\n- [Getting Started](#getting-tarted)\n- [Running](#running)\n- [References](#references)\n- [Citations](#citation)\n\n## Getting Started\n\n- Clone the repository\n\n### Prerequisites\n\n- Tensorflow 2.2.0+\n- Tensorflow_addons\n- Python 3.6+\n- Keras 2.3.0\n- PIL\n- numpy\n\n```python\npip install -r requirements.txt\n```\n\n## Running\n### Training \n- Preprocess\n    - Download the [training data](https://cseweb.ucsd.edu/~viscomp/projects/SIG17HDR/PaperData/SIGGRAPH17_HDR_Trainingset.zip) and [testing data](https://cseweb.ucsd.edu/~viscomp/projects/SIG17HDR/PaperData/SIGGRAPH17_HDR_Testset.zip).\n\n    - Run this file to generate data. (Please remember to change path first)\n\n    ```\n    python src/create_dataset.py\n    ```\n\n- Train ANL-HDRI \n    ```\n    python main.py\n    ```\n\n- Test ANL-HDRI\n    - Download weights [here](https://drive.google.com/file/d/1G94mGLbKSLcvzl9CRs5WY305meG13pWh/view?usp=sharing)\n    ```\n    python test.py --weight_test_path ANLNet.h5 --test_path Test/EXTRA/001/\n    ```\n## Usage\n### Training\n```\nusage: main.py [-h] [--images_path IMAGES_PATH] [--test_path TEST_PATH]\n               [--lr LR] [--gpu GPU] [--num_epochs NUM_EPOCHS] \n               [--train_batch_size TRAIN_BATCH_SIZE]\n               [--display_ep DISPLAY_EP] [--checkpoint_ep CHECKPOINT_EP]\n               [--checkpoints_folder CHECKPOINTS_FOLDER]\n               [--load_pretrain LOAD_PRETRAIN] [--pretrain_dir PRETRAIN_DIR]\n               [--filter FILTER] [--kernel KERNEL]\n               [--encoder_kernel ENCODER_KERNEL]\n               [--decoder_kernel DECODER_KERNEL]\n               [--triple_pass_filter TRIPLE_PASS_FILTER]\n```\n\n```\noptional arguments: -h, --help                show this help message and exit\n                    --images_path             training path\n                    --lr                      LR\n                    --gpu                     GPU\n                    --num_epochs              NUM of EPOCHS\n                    --train_batch_size        training batch size\n                    --display_ep              display result every \"x\" epoch\n                    --checkpoint_ep           save weights every \"x\" epoch\n                    --checkpoints_folder      folder to save weight\n                    --load_pretrain           load pretrained model\n                    --pretrain_dir            pretrained model folder\n                    --filter                  default filter\n                    --kernel                  default kernel\n                    --encoder_kernel          encoder filter size\n                    --decoder_kernel          decoder filter size\n                    --triple_pass_filter      number of filter in triple pass\n```\n\n### Testing\n\u003c!--- Download the weight [here](https://drive.google.com/file/d/1OjJYirwRa8cLGzzdRYRkjq_1FokyI80V/view?usp=sharing) and put it to the folder. ---\u003e\nThe weight file was deprecated. Will be updated soon.\n```\nusage: test.py [-h] [--test_path TEST_PATH] [--gpu GPU]\n                    [--weight_test_path WEIGHT_TEST_PATH] [--filter FILTER]\n                    [--kernel KERNEL] [--encoder_kernel ENCODER_KERNEL]\n                    [--decoder_kernel DECODER_KERNEL]\n                    [--triple_pass_filter TRIPLE_PASS_FILTER]\n```\n```\noptional arguments: -h, --help                    show this help message and exit\n                    --test_path                   test path\n                    --weight_test_path            weight test path\n                    --filter                      default filter\n                    --kernel                      default kernel\n                    --encoder_kernel              encoder filter size\n                    --decoder_kernel              decoder filter size\n                    --triple_pass_filter          number of filter in triple pass\n```\n\n#### Result\n![DEMO0](teaser/rs1.png) \n![DEMO1](teaser/rs2.png) \n![DEMO2](teaser/rs3.png) \n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](https://github.com/tuvovan/ANL-HDRI/blob/master/LICENSE) file for details\n\n## References\n[1] Training and Testing dataset - [link](https://cseweb.ucsd.edu/~viscomp/projects/SIG17HDR/)\n\n## Citation\n```\n    @ARTICLE{8989959,  author={Tu V.V},   \n    title={High Dynamic Range Image Synthesis via Attention Non-Local Network},   \n    year={2020},  \n    url={github.com/tuvovan/ANL-HDRI},}\n```\n## Acknowledgments\n- My work is done on my sparse time so I should have some mistake or further possible improvement.\n- Any ideas on updating or misunderstanding, please send me an email: \u003cvovantu.hust@gmail.com\u003e\n- If you find this repo helpful, kindly give me a star.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftuvovan%2Fanl-hdri","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftuvovan%2Fanl-hdri","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftuvovan%2Fanl-hdri/lists"}