{"id":49115997,"url":"https://github.com/yzqin/dexpoint-release","last_synced_at":"2026-04-21T07:11:08.089Z","repository":{"id":173493989,"uuid":"626044770","full_name":"yzqin/dexpoint-release","owner":"yzqin","description":"DexPoint: Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Manipulation, CoRL 2022","archived":false,"fork":false,"pushed_at":"2024-05-22T21:44:00.000Z","size":44689,"stargazers_count":100,"open_issues_count":1,"forks_count":12,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-03-28T12:36:51.530Z","etag":null,"topics":["dexterous-manipulation","pointcloud","reinforcement-learning","sim2real"],"latest_commit_sha":null,"homepage":"https://yzqin.github.io/dexpoint/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/yzqin.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2023-04-10T17:20:13.000Z","updated_at":"2026-02-24T18:05:32.000Z","dependencies_parsed_at":"2025-04-11T23:59:29.697Z","dependency_job_id":null,"html_url":"https://github.com/yzqin/dexpoint-release","commit_stats":null,"previous_names":["yzqin/dexpoint-release"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/yzqin/dexpoint-release","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yzqin%2Fdexpoint-release","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yzqin%2Fdexpoint-release/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yzqin%2Fdexpoint-release/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yzqin%2Fdexpoint-release/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/yzqin","download_url":"https://codeload.github.com/yzqin/dexpoint-release/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yzqin%2Fdexpoint-release/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32081230,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-21T06:27:27.065Z","status":"ssl_error","status_checked_at":"2026-04-21T06:27:21.250Z","response_time":128,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["dexterous-manipulation","pointcloud","reinforcement-learning","sim2real"],"created_at":"2026-04-21T07:11:05.751Z","updated_at":"2026-04-21T07:11:08.080Z","avatar_url":"https://github.com/yzqin.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# DexPoint: Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Manipulation \n\n[[Project Page]](https://yzqin.github.io/dexpoint/) [[Paper]](https://arxiv.org/abs/2211.09423) [[Poster]](https://docs.google.com/presentation/d/1dDtAPQ49k1emhETRPAib5R0wCGdwlz5l/edit?usp=sharing\u0026ouid=108317450590466198031\u0026rtpof=true\u0026sd=true)[[ShapeNet Object Models]](https://drive.google.com/file/d/1liqE8Zin4tAlfFcJBIpT1Qn2Nyzl3Nke/view?usp=sharing)\n-----\n\n[DexPoint: Generalizable Point Cloud Reinforcement Learning for\nSim-to-Real Dexterous Manipulation ](https://yzqin.github.io/dexpoint/)\n\nYuzhe Qin*, Binghao Huang*, Zhao-Heng Yin, Hao Su, Xiaolong Wang, CoRL 2022.\n\nDexPoint is a novel system and algorithm for RL from point cloud. This repo contains the simulated environment and\ntraining code for DexPoint.\n\n![Teaser](docs/teaser.png)\n\n## Bibtex\n\n```\n@article{dexpoint,\n  title          = {DexPoint: Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Manipulation },\n  author         = {Qin, Yuzhe and Huang, Binghao and Yin, Zhao-Heng and Su, Hao and Wang, Xiaolong},\n  journal        = {Conference on Robot Learning (CoRL)},\n  year           = {2022},\n}\n```\n\n## Installation\n\n```shell\ngit clone git@github.com:yzqin/dexpoint-release.git\ncd dexart-release\nconda create --name dexpoint python=3.8\nconda activate dexpoint\npip install -e .\n```\n\nDownload data file for the scene\nfrom [Google Drive Link](https://drive.google.com/file/d/1Xe3jgcIUZm_8yaFUsHnO7WJWr8cV41fE/view?usp=sharing).\nPlace the `day.ktx` at `assets/misc/ktx/day.ktx`.\n\n```shell\npip install gdown\ngdown https://drive.google.com/uc?id=1Xe3jgcIUZm_8yaFUsHnO7WJWr8cV41fE\n```\n\n## File Structure\n\n- `dexpoint`: main content for the environment, utils, and other staff needs for RL training.\n- `assets`: robot and object models, and other static files\n- `example`: entry files to learn how to use the DexPoint environment\n- `docker`: dockerfile that can create container to be used for headless training on server\n\n## Quick Start\n\n### Use DexPoint environment and extend it for your project\n\nRun and explore the comments in the file below provided to familiarize yourself with the basic architecture of the\nDexPoint environment. Check the printed messages to understand the observation, action, camera, and speed for these\nenvironments.\n\n- [state_only_env.py](example/example_use_state_only_env.py): minimal state only environment\n- [example_use_pc_env.py](example/example_use_pc_env.py): minimal point cloud environment\n- [example_use_imagination_env.py](example/example_use_imagination_env.py): point cloud environment with imagined point\n  proposed\n  in DexPoint\n- [example_use_multi_camera_visual_env.py](example/example_use_multi_camera_visual_env.py): environment with multiple\n  different visual modalities, including depth, rgb, segmentation. We provide it for your reference, although it is not\n  used in DexPoint\n\nThe environment we used in the training of DexPoint paper can be found here\nin [example_dexpoint_grasping.py](example/example_dexpoint_grasping.py).\n\n### Training\n\nDownload the ShapeNet models from [Google Drive](https://drive.google.com/file/d/1liqE8Zin4tAlfFcJBIpT1Qn2Nyzl3Nke/view?usp=sharing) can place it inside the following directory `dexpoint-release/assets/shapenet/`.\n\nThe `DexPoint` repo is using the same training code as [DexArt](https://github.com/Kami-code/dexart-release) and environment interface for RL training. Please check the training code [here](https://github.com/Kami-code/dexart-release/tree/main/stable_baselines3) to train DexPoint with PPO.\n\n## Acknowledgements\n\nWe would like to thank the following people for making this project possible:\n\n- [Tongzhou Mu](https://cseweb.ucsd.edu//~t3mu/) and [Ruihan Yang](https://rchalyang.github.io/) for helpful discussion\n  and feedback.\n- [Fanbo Xiang](https://www.fbxiang.com/) for invaluable help on rendering.\n\n### Example extension of DexPoint environment framework in other project\n\n[DexArt: Benchmarking Generalizable Dexterous Manipulation with Articulated Objects (CVPR 2023)](https://github.com/Kami-code/dexart-release):\nextend DexPoint to articulated object manipulation.\n\n[From One Hand to Multiple Hands: Imitation Learning for Dexterous Manipulation from Single-Camera Teleoperation (RA-L 2022)](https://github.com/yzqin/dex-hand-teleop):\nuse teleoperation for data collection in DexPoint environment.\n\n\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyzqin%2Fdexpoint-release","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyzqin%2Fdexpoint-release","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyzqin%2Fdexpoint-release/lists"}