{"id":13497366,"url":"https://github.com/mjiUST/SurfaceNet","last_synced_at":"2025-03-28T21:32:30.298Z","repository":{"id":215966868,"uuid":"99289655","full_name":"mjiUST/SurfaceNet","owner":"mjiUST","description":"2017 ICCV, SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsis","archived":false,"fork":false,"pushed_at":"2020-07-14T07:04:53.000Z","size":9739,"stargazers_count":123,"open_issues_count":8,"forks_count":36,"subscribers_count":9,"default_branch":"github.SurfaceNet","last_synced_at":"2024-10-31T13:34:23.939Z","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/mjiUST.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","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":"2017-08-04T01:25:53.000Z","updated_at":"2024-09-13T10:00:14.000Z","dependencies_parsed_at":null,"dependency_job_id":"7dfd5e1d-3cc9-40ed-8f52-5394ee214b6a","html_url":"https://github.com/mjiUST/SurfaceNet","commit_stats":null,"previous_names":["mjiust/surfacenet"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mjiUST%2FSurfaceNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mjiUST%2FSurfaceNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mjiUST%2FSurfaceNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mjiUST%2FSurfaceNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mjiUST","download_url":"https://codeload.github.com/mjiUST/SurfaceNet/tar.gz/refs/heads/github.SurfaceNet","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246105636,"owners_count":20724338,"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":"2024-07-31T20:00:29.817Z","updated_at":"2025-03-28T21:32:28.886Z","avatar_url":"https://github.com/mjiUST.png","language":"Python","readme":"# News\n- [SurfaceNet+](https://github.com/mjiUST/SurfaceNet-plus) is available in 2020 TPAMI!\n\n# SurfaceNet\n\nM. Ji, J. Gall, H. Zheng, Y. Liu, and L. Fang. [SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsis](https://www.researchgate.net/publication/318920947_SurfaceNet_An_End-to-end_3D_Neural_Network_for_Multiview_Stereopsis). ICCV, 2017\n\nThe [poster pdf](https://www.researchgate.net/publication/321126305_ICCV2017_SurfaceNet_poster) is also available.\n\n![SurfaceNet experiment results](figures/experiment.png?raw=true \"SurfaceNet experiment results\")\n![SurfaceNet pipeline](figures/pipeline.png?raw=true \"SurfaceNet pipeline\")\n\n## How to run\n\n1. install [Nvidia driver 375 + cuda 8.0 + cudnn v5.1](https://github.com/mjiUST/driver_cuda_cudnn)\n2. install the conda environment by: `bash installEnv.sh`\n    * DON'T WORRY, conda will generate an isolated environment for SurfaceNet with python2.7, anaconda, theano, ... etc. That means all your libraries / packeges' version will not be affacted, at the same time the `~/.bashrc` file will not be changed.\n    * before you run, PLEASE change the CUDA/CUDNN path in the files: \n        - `./config/activate-cuda.sh` change the 1st line to your cuda path, e.g.: `export CUDA_ROOT=/usr/local/cuda`\n        - `./config/activate-cudnn.sh` change the 1st line to your cudnn path, e.g.: `export CUDNN_ROOT=/home/\u003cyour-user-name\u003e/libs/cudnn`\n3. download the network model to the folder \"./inputs/SurfaceNet_models\" from the Dropbox [folder](https://www.dropbox.com/sh/8xs0u57ikj4qfvr/AADRQFQyJfG3WfH7ZvpcWmMKa?dl=0)\n4. if the conda environment has been installed, one can activate it by: `. activate SurfaceNet`; deactivate it by: `. deactivate`.\n5. in terminal run: `python main.py` \n\n## Evaluation results\n\nSome evaluation results are uploaded, including '.ply' files and the detailed number of Table 3. This could be helpful if you want to compare with this work.\n\n## License\n\nSurfaceNet is released under the MIT License (refer to the LICENSE file for details).\n\n## Citing SurfaceNet\n\nIf you find SurfaceNet useful in your research, please consider citing:\n\n    @inproceedings{ji2017surfacenet,\n      title={SurfaceNet: An End-To-End 3D Neural Network for Multiview Stereopsis},\n      author={Ji, Mengqi and Gall, Juergen and Zheng, Haitian and Liu, Yebin and Fang, Lu},\n      booktitle={Proceedings of the IEEE International Conference on Computer Vision (ICCV)},\n      pages={2307--2315},\n      year={2017}\n    }\n","funding_links":[],"categories":["3DVision","Multi-view Stereo","Multiple View Stereovision"],"sub_categories":["Depth/StereoMatching","paper","Machine Learning based MVS"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FmjiUST%2FSurfaceNet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FmjiUST%2FSurfaceNet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FmjiUST%2FSurfaceNet/lists"}