{"id":19134281,"url":"https://github.com/um-arm-lab/mps_shape_completion","last_synced_at":"2026-06-23T14:32:10.943Z","repository":{"id":79650992,"uuid":"176823831","full_name":"UM-ARM-Lab/mps_shape_completion","owner":"UM-ARM-Lab","description":"Neural network completion of partial shapes in a voxel grid","archived":false,"fork":false,"pushed_at":"2021-01-22T21:59:53.000Z","size":819,"stargazers_count":1,"open_issues_count":2,"forks_count":0,"subscribers_count":9,"default_branch":"master","last_synced_at":"2025-11-13T14:38:03.049Z","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":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/UM-ARM-Lab.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,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-03-20T22:01:30.000Z","updated_at":"2020-10-19T02:09:21.000Z","dependencies_parsed_at":"2023-05-14T09:15:35.314Z","dependency_job_id":null,"html_url":"https://github.com/UM-ARM-Lab/mps_shape_completion","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/UM-ARM-Lab/mps_shape_completion","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UM-ARM-Lab%2Fmps_shape_completion","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UM-ARM-Lab%2Fmps_shape_completion/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UM-ARM-Lab%2Fmps_shape_completion/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UM-ARM-Lab%2Fmps_shape_completion/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/UM-ARM-Lab","download_url":"https://codeload.github.com/UM-ARM-Lab/mps_shape_completion/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UM-ARM-Lab%2Fmps_shape_completion/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34694780,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-23T02:00:07.161Z","response_time":65,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":"2024-11-09T06:26:06.110Z","updated_at":"2026-06-23T14:32:10.909Z","avatar_url":"https://github.com/UM-ARM-Lab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Shape-completion\n\nMPS Shape Completion is a neural network that takes in a grid of visible occupied voxels and outputs a grid of voxels the NN believes are occupied, thus \"completing the shape\". \nThis has been used in the \"Moving Piles of Stuff\" project.\n\n[![Build Status](https://travis-ci.com/UM-ARM-Lab/mps_shape_completion.svg?branch=master)](https://travis-ci.com/UM-ARM-Lab/mps_shape_completion)\n\n## Setup\n\n### Prerequisites\nThe code is developed and tested on\n- [`CUDA`](https://developer.nvidia.com/cuda-toolkit) 9.0 \n- [`cuDNN`](https://developer.nvidia.com/rdp/cudnn-archive) 7.0.5\n- [`Python`](https://www.python.org) 2.7.12\n- [`TensorFlow`](https://github.com/tensorflow/tensorflow) 1.7.0, 1.15.0\n- [`numpy`](http://www.numpy.org/) 1.14.2\n- [`ROS`](http://wiki.ros.org/kinetic) kinetic\n\n### Initial Demo\n\n1. Clone this repo into a catkin workspace. Rebuild and resource.\n2. Download the pretrained model into the `train_mod` folder from [this link](https://drive.google.com/file/d/1Kmij09eHVE3ab5s7Vnp-fI-qOCLei4u0/view?usp=sharing), or use the download script `download_model.sh`\n2. View the input files: `./viewvox demo/occupy.binvox`\n3. Start a roscore: `roscore`\n4. In another terminal start the shape_completion_node `rosrun mps_shape_completion shape_completion_node.py`.\nThe model should load. This may take a minute.\n5. In another terminal window run the ros demo: `rosrun mps_shape_completion ros_demo.py`.\nThe output should be saved to `demo/output.binvox`\n6. View the output: `./viewvox demo/output.binvox`\n\n### Normal use\nIn normal operation just start a `shape_completion_node.py`. Requests are made either through a ros service call or a ros message via a publisher.\n\n## Overview\n- `shape_completion.py`: provides a class that uses the trained model to do shape completion.\n- `train_mod/`: contains the model.\n- `demo/`: contains sample input in the shape_completion demo. \n- `binvox_rw/`: Python module to read and write .binvox files. [dimatura/binvox-rw-py](https://github.com/dimatura/binvox-rw-py)\n- `viewvox`: Reads a 3D voxel file as produced by binvox or thinvox and shows it in a window. [3D voxel model viewer](http://www.patrickmin.com/viewvox/)\n\n- The current model is trained on a subset of objects in ycb dataset and shapenet:\n\n![](https://github.com/UM-ARM-Lab/Shape-completion/blob/master/train_mod/training_set.png)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fum-arm-lab%2Fmps_shape_completion","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fum-arm-lab%2Fmps_shape_completion","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fum-arm-lab%2Fmps_shape_completion/lists"}