{"id":13444078,"url":"https://github.com/NVlabs/splatnet","last_synced_at":"2025-03-20T17:33:07.808Z","repository":{"id":78251908,"uuid":"137399783","full_name":"NVlabs/splatnet","owner":"NVlabs","description":"SPLATNet: Sparse Lattice Networks for Point Cloud Processing (CVPR2018)","archived":false,"fork":false,"pushed_at":"2020-10-16T04:28:08.000Z","size":42,"stargazers_count":267,"open_issues_count":10,"forks_count":53,"subscribers_count":21,"default_branch":"master","last_synced_at":"2024-10-28T07:42:43.334Z","etag":null,"topics":["3d","cvpr2018","deep-learning","joint-2d-3d","point-cloud"],"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/NVlabs.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2018-06-14T19:24:13.000Z","updated_at":"2024-05-20T12:23:53.000Z","dependencies_parsed_at":"2023-05-29T03:30:29.713Z","dependency_job_id":null,"html_url":"https://github.com/NVlabs/splatnet","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/NVlabs%2Fsplatnet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVlabs%2Fsplatnet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVlabs%2Fsplatnet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVlabs%2Fsplatnet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/NVlabs","download_url":"https://codeload.github.com/NVlabs/splatnet/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244660995,"owners_count":20489444,"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":["3d","cvpr2018","deep-learning","joint-2d-3d","point-cloud"],"created_at":"2024-07-31T03:02:18.411Z","updated_at":"2025-03-20T17:33:07.472Z","avatar_url":"https://github.com/NVlabs.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"## SPLATNet: Sparse Lattice Networks for Point Cloud Processing (CVPR2018)\n\n### License\n\nCopyright (C) 2018 NVIDIA Corporation.  All rights reserved.\nLicensed under the CC BY-NC-SA 4.0 license (https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode). \n\n\n### Paper\n[arXiv](https://arxiv.org/abs/1802.08275)\n```\n@inproceedings{su18splatnet,\n  author={Su, Hang and Jampani, Varun and Sun, Deqing and Maji, Subhransu and Kalogerakis, Evangelos and Yang, Ming-Hsuan and Kautz, Jan},\n  title     = {{SPLATN}et: Sparse Lattice Networks for Point Cloud Processing},\n  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},\n  pages     = {2530--2539},\n  year      = {2018}\n}\n```\n\n### Usage\n       \n1. Install [Caffe](http://caffe.berkeleyvision.org) and [bilateralNN](https://github.com/MPI-IS/bilateralNN)\n    \n    Note that our code uses Python3. \n    * Please follow the instructions on the [bilateralNN](https://github.com/MPI-IS/bilateralNN) repo. \n    * A step-by-step installation guide for Ubuntu 16.04 is provided in [INSTALL.md](INSTALL.md). \n    * Alternatively, you can install [nvidia-docker](https://github.com/NVIDIA/nvidia-docker) and use this docker image: \n        ```bash\n        docker pull suhangpro/caffe:bpcn\n        ``` \n        You can also build this image with the [Dockerfile](Dockerfile). \n    * The docker image provided above uses CUDA 8, which is no longer supported if you have Volta GPUs (e.g. Titan V), Turing GPUs (e.g. RTX 2080), or newer ones. Adapting the Dockerfile to more recent GPUs should be straightforward—check out the [example](https://hub.docker.com/repository/docker/zyzwhdx/splatnet/general) supporting up to Turing, courtesy of @zyzwhdx.\n\n2. Include the project to your python path so imports can be found, e.g. \n    ```bash\n    export PYTHONPATH=\u003cPATH_TO_PROJECT_ROOT\u003e:$PYTHONPATH\n    ```\n\n3. Download and prepare data files under folder `data/`\n    \n    See instructions in data/[README.md](data/README.md).\n    \n4. Usage examples\n    * 3D facade segmentation\n        * test pre-trained model\n            ```bash\n            cd exp/facade3d\n            ./dl_model_facade3d.sh  # download pre-trained model\n            SKIP_TRAIN=1 ./train_test.sh\n            ```\n            Prediction is output at `pred_test.ply`, with evaluation results in `test.log`.\n        * or, train and evaluate\n            ```bash\n            cd exp/facade3d\n            ./train_test.sh\n            ```\n    * ShapeNet Part segmentation\n        * test pre-trained model\n            ```bash\n            cd exp/shapenet3d\n            ./dl_model_shapenet3d.sh  # download pre-trained model\n            ./test_only.sh\n            ```\n            Predictions are under `pred/`, with evaluation results in `test.log`.\n        * or, train and evaluate\n            ```bash\n            cd exp/shapenet3d\n            ./train_test.sh\n            ```\n\n### References \nWe make extensive use of bilateralNN, which is proposed in these publications:\n* V. Jampani, M. Kiefel and P. V. Gehler. Learning Sparse High-Dimensional Filters: Image Filtering, Dense CRFs and Bilateral Neural Networks. CVPR, 2016.\n* M.Kiefel, V. Jampani and P. V. Gehler. Permutohedral Lattice CNNs. ICLR Workshops, 2015.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FNVlabs%2Fsplatnet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FNVlabs%2Fsplatnet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FNVlabs%2Fsplatnet/lists"}