{"id":13608101,"url":"https://github.com/wzh99/DCP-TF","last_synced_at":"2025-04-12T14:32:09.078Z","repository":{"id":69775364,"uuid":"268493170","full_name":"wzh99/DCP-TF","owner":"wzh99","description":"SJTU CS473 Project: Implementation of Deep Closest Point in TensorFlow, and its comparison with other registration methods.","archived":false,"fork":false,"pushed_at":"2020-06-14T08:20:40.000Z","size":8748,"stargazers_count":12,"open_issues_count":0,"forks_count":1,"subscribers_count":3,"default_branch":"master","last_synced_at":"2024-11-07T13:39:23.771Z","etag":null,"topics":["deep-learning","point-cloud-registration","tensorflow","tensorflow-graphics"],"latest_commit_sha":null,"homepage":"","language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/wzh99.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2020-06-01T10:37:57.000Z","updated_at":"2024-06-12T00:29:30.000Z","dependencies_parsed_at":null,"dependency_job_id":"d97e6dd0-f65e-40e9-bec8-1d2403abe3ee","html_url":"https://github.com/wzh99/DCP-TF","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/wzh99%2FDCP-TF","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wzh99%2FDCP-TF/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wzh99%2FDCP-TF/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wzh99%2FDCP-TF/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/wzh99","download_url":"https://codeload.github.com/wzh99/DCP-TF/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248581270,"owners_count":21128138,"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":["deep-learning","point-cloud-registration","tensorflow","tensorflow-graphics"],"created_at":"2024-08-01T19:01:24.264Z","updated_at":"2025-04-12T14:32:06.062Z","avatar_url":"https://github.com/wzh99.png","language":"C++","funding_links":[],"categories":["资源清单"],"sub_categories":["CS3301 (原 CS473) - GPU计算及深度学习"],"readme":"# Deep Closest Point in TensorFlow\n\n## Introduction\n\nThis project implements [Deep Closest Point](https://arxiv.org/abs/1905.03304) model in TensorFlow. It also includes C++ code that compare its performance with other registration methods (ICP, 4-PCS, Go-ICP).\n\n## Dependencies\n\nTo run DCP model, you may have to install these Python packages:\n\n* tensorflow\u003e=2.0.0\n* tensorflow-graphics (none of its dependencies is required)\n* numpy\n* h5py\n\nTo run comparison program, you may have to install these libraries:\n\n* PCL 1.9 (and its dependencies)\n* HDF5\n* TBB\n\n## Usage\n\nBasic usage is encapsulated into procedures. You can directly call them in the program. Hyperparameters are directly defined in source code, and command line arguments is not supported.\n\n### Dataset\n\nDownload [ModelNet40](https://shapenet.cs.stanford.edu/media/modelnet40_ply_hdf5_2048.zip) and unzip files into directory `modelnet40`. Run `util.pack_to_one()` to pack all dataset files into single `train.h5` and `test.h5` files. \n\n### Training and evaluation\n\nTrained weights `dcp_v2.h5` can be unzipped from [`weights/dcp_v2.zip`](weights/dcp_v2.zip). Place it in `weights` directory so that evaluation and testing procedure can find it. If you want to train by yourself, run `train.train()` to train, or your owning training procedure. Run `train.evaluate()` to evaluate the trained model with test dataset.\n\n### Comparison\n\nThe comparison program tests registration methods on the first 100 models of the test dataset. It is divided into Python and C++ code. Run `compare.test_dcp()` to test DCP. Compile and run the C++ program to test ICP, 4-PCS and Go-ICP. ICP and 4-PCS implementation is from PCL. Go-ICP is from my previous project [OptICP](https://github.com/wzh99/OptICP).\n\n## Documentation\n\nThe project [proposal](doc/proposal.md) and [report](doc/dcp_report.md) are provided (both in Chinese). Refer to them for better understanding of this project. \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwzh99%2FDCP-TF","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwzh99%2FDCP-TF","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwzh99%2FDCP-TF/lists"}