{"id":13857083,"url":"https://github.com/iyah4888/SIGGRAPH18SSS","last_synced_at":"2025-07-13T20:30:39.608Z","repository":{"id":150418660,"uuid":"142793920","full_name":"iyah4888/SIGGRAPH18SSS","owner":"iyah4888","description":"SIGGRAPH2018, Semantic Soft Segmentation, http://people.inf.ethz.ch/aksoyy/sss/","archived":false,"fork":false,"pushed_at":"2020-09-07T22:54:34.000Z","size":1175,"stargazers_count":456,"open_issues_count":7,"forks_count":107,"subscribers_count":24,"default_branch":"master","last_synced_at":"2024-05-19T23:35:51.801Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/iyah4888.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}},"created_at":"2018-07-29T20:41:08.000Z","updated_at":"2024-05-19T05:43:08.000Z","dependencies_parsed_at":"2023-05-17T22:45:32.441Z","dependency_job_id":null,"html_url":"https://github.com/iyah4888/SIGGRAPH18SSS","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/iyah4888%2FSIGGRAPH18SSS","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iyah4888%2FSIGGRAPH18SSS/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iyah4888%2FSIGGRAPH18SSS/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iyah4888%2FSIGGRAPH18SSS/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/iyah4888","download_url":"https://codeload.github.com/iyah4888/SIGGRAPH18SSS/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":213988315,"owners_count":15666961,"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":"2024-08-05T03:01:25.284Z","updated_at":"2024-08-05T03:02:44.764Z","avatar_url":"https://github.com/iyah4888.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"## Important Note:\n**This repository alone is not a complete code. Please also check the repository for segmentation part [[here](https://github.com/yaksoy/SemanticSoftSegmentation)].**\n\n**Also, please readme README carefully.**\n\n# Semantic Soft Segmentation, ACM SIGGRAPH 2018\n\nThis repository includes the semantic feature (128-D) generation approach presented in\n\n    Yagiz Aksoy, Tae-Hyun Oh, Sylvain Paris, Marc Pollefeys and Wojciech Matusik, \"Semantic Soft Segmentation\", ACM Transactions on Graphics (Proc. SIGGRAPH), 2018 \n\nAlso, note that this repository is NOT **stand-alone**. \nThe spectral segmentation implementation can be found [[here](https://github.com/yaksoy/SemanticSoftSegmentation)].\nThe low-dimension projection to 3-dimension and its filtering code are available in the repository.\n\nPlease refer to the [[project page](http://people.inf.ethz.ch/aksoyy/sss/)] for more information.\n\nNote that only the feature generator is presented in this repository and the training code is not included.\n\n# Requirements\nPython 3.6, 1.8 \u003e= TensorFlow \u003e= 1.4 and other common packages listed in requirements.txt.\n\nThe code has been tested on {Linux Ubuntu 16.04, TensorFlow-GPU 1.4} and {Windows 10, TensorFlow-GPU 1.8} with Titan Xp.\n\n# Installation\n1. Install dependencies\n```\npip3 install -r requirements.txt\n```\n2. Clone or download this repository.\n3. Download the [pre-trained](http://cvg.ethz.ch/research/semantic-soft-segmentation/SSS_model.zip) model.\n4. Extract the model and put the extracted \"model\" folder into the folder where the repository is cloned.\n   - e.g., If the repository is cloned at \"/project/sss\", then move the model to be \"/project/sss/model\")\n5. Run \"run_extract_feat.sh\", which will process sample images in the \"samples\" folder. If you want to run your own images, notice that image files should be the PNG formats.\n\n\n# Notes\nCurrently, the code only supports the PNG file format.\n\n# Citation\nIf you use this code, please cite our paper:\n\n```\n@ARTICLE{sss,\nauthor={Ya\\u{g}{\\i}z Aksoy and Tae-Hyun Oh and Sylvain Paris and Marc Pollefeys and Wojciech Matusik},\ntitle={Semantic Soft Segmentation},\njournal={ACM Transactions on Graphics (Proc. SIGGRAPH)},\nyear={2018},\npages = {72:1-72:13},\nvolume = {37},\nnumber = {4}\n}\n```\nThis code is for protyping research ideas; thus, please use this code only for non-commercial purpose only.  \n\n# Credits\nThe part of the base codes (the tools in the \"deeplab_resnet\" directory) are borrowed from [(Re-)implementation of DeepLab-ResNet-TensorFlow](https://github.com/DrSleep/tensorflow-deeplab-resnet#using-your-dataset)\nLikewise, our code (the tools in \"kaffe\" directory) is benefited from [Caffe to TensorFlow](https://github.com/ethereon/caffe-tensorflow)\n\nAlso, our architecture is implemented on top of the base architecture, DeepLab-ResNet-101.\n\n```\n@article{CP2016Deeplab,\n      title={DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs},\n      author={Liang-Chieh Chen and George Papandreou and Iasonas Kokkinos and Kevin Murphy and Alan L Yuille},\n      journal={arXiv:1606.00915},\n      year={2016}\n    }\n```\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fiyah4888%2FSIGGRAPH18SSS","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fiyah4888%2FSIGGRAPH18SSS","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fiyah4888%2FSIGGRAPH18SSS/lists"}