{"id":19134381,"url":"https://github.com/um-arm-lab/contact_shape_completion","last_synced_at":"2025-11-12T22:02:30.869Z","repository":{"id":47171438,"uuid":"311698477","full_name":"UM-ARM-Lab/contact_shape_completion","owner":"UM-ARM-Lab","description":"Shape completion using contact measurements. Successor of PSSNet","archived":false,"fork":false,"pushed_at":"2021-10-24T23:05:24.000Z","size":6903,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":11,"default_branch":"main","last_synced_at":"2025-02-22T17:48:09.666Z","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}},"created_at":"2020-11-10T15:18:22.000Z","updated_at":"2021-10-24T23:05:27.000Z","dependencies_parsed_at":"2022-09-04T03:41:29.722Z","dependency_job_id":null,"html_url":"https://github.com/UM-ARM-Lab/contact_shape_completion","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/UM-ARM-Lab/contact_shape_completion","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UM-ARM-Lab%2Fcontact_shape_completion","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UM-ARM-Lab%2Fcontact_shape_completion/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UM-ARM-Lab%2Fcontact_shape_completion/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UM-ARM-Lab%2Fcontact_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/contact_shape_completion/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UM-ARM-Lab%2Fcontact_shape_completion/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":284115870,"owners_count":26949957,"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","status":"online","status_checked_at":"2025-11-12T02:00:06.336Z","response_time":59,"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":"2024-11-09T06:26:25.394Z","updated_at":"2025-11-12T22:02:30.840Z","avatar_url":"https://github.com/UM-ARM-Lab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# CLASP\n\nConstrained LAtent Shape Projection (CLASP) combines a shape completion neural network with contact measurements from a robot. This repo also contains the [full paper](https://github.com/UM-ARM-Lab/contact_shape_completion/blob/main/CLASP_full.pdf) and [additional plots](https://github.com/UM-ARM-Lab/contact_shape_completion/blob/main/CLASP_additional_details.pdf).\n\n\n# Quick Start\n1. Set up ROS\n2. Clone this repo in your ROS path. Rebuild (e.g. catkin build), re-source\n3. Install dependencies\n4. Download datasets and pretrained models by running `shape_completion_training/scripts/download_pretrained.py`\n\n### Data Analysis\nTrial results are in `./evaluations`\nTo recreate the plots from the paper using the pre-run trials, `contact_completion_evaluation.py --plot`\n\n\n### Rerun shape completion experiments and visualize performance\nTo rerun shape completion experiments using the robot motion and contacts as recorded from the paper, in separate terminals run:\n1. `roslaunch shape_completion_visualization live_shape_completion.launch` (Rviz will start)\n2. `roslaunch shape_completion_visualization transforms.launch` (Sets transforms between robot and shape objects)\n3. `contact_completion_evaluation.py --plot --regenerate`  (You will see many shape being generated and updates. Will take over an hour to complete)\n\n\n# Full Stack\nThe full experimental setup requires running a simulated, or real robot, which moves and contacts objects.\nTo build the software stack used in the experiments, set up the dependencies.\n\nDetailed instructions are in the subfolder [https://github.com/UM-ARM-Lab/contact_shape_completion/tree/main/contact_shape_completion]\n\nThen run\n1. `roslaunch shape_completion_visualization live_shape_completion.launch` (Rviz will start)\n2. Launch the robot stack (see detailed instructions in subfolder)\n3. `store_simulation_examples --trial [PRETRAINED_NETWORK_NAME] --scene [SCENE_NAME] --store`\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fum-arm-lab%2Fcontact_shape_completion","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fum-arm-lab%2Fcontact_shape_completion","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fum-arm-lab%2Fcontact_shape_completion/lists"}