{"id":13958519,"url":"https://github.com/facebookresearch/house3d","last_synced_at":"2025-09-27T07:30:24.922Z","repository":{"id":38421917,"uuid":"112513665","full_name":"facebookresearch/House3D","owner":"facebookresearch","description":"a Realistic and Rich 3D Environment","archived":true,"fork":false,"pushed_at":"2020-07-06T04:41:49.000Z","size":677,"stargazers_count":1193,"open_issues_count":10,"forks_count":186,"subscribers_count":68,"default_branch":"master","last_synced_at":"2024-12-17T01:37:34.318Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/facebookresearch.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2017-11-29T18:41:51.000Z","updated_at":"2024-12-09T07:30:48.000Z","dependencies_parsed_at":"2022-07-11T19:25:09.841Z","dependency_job_id":null,"html_url":"https://github.com/facebookresearch/House3D","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/facebookresearch%2FHouse3D","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/facebookresearch%2FHouse3D/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/facebookresearch%2FHouse3D/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/facebookresearch%2FHouse3D/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/facebookresearch","download_url":"https://codeload.github.com/facebookresearch/House3D/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":234402324,"owners_count":18826737,"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":[],"created_at":"2024-08-08T13:01:41.651Z","updated_at":"2025-09-27T07:30:24.049Z","avatar_url":"https://github.com/facebookresearch.png","language":"C++","funding_links":[],"categories":["时间序列"],"sub_categories":["网络服务_其他"],"readme":"# House3D: A Rich and Realistic 3D Environment\n#### [Yi Wu](https://jxwuyi.weebly.com/), [Yuxin Wu](https://github.com/ppwwyyxx), [Georgia Gkioxari](https://gkioxari.github.io/) and [Yuandong Tian](http://yuandong-tian.com/)\n#\n\n\u003cp align=\"center\"\u003e\u003cimg src=\"https://user-images.githubusercontent.com/1381301/33509559-87c4e470-d6b7-11e7-8266-27c940d5729a.jpg\" align=\"middle\" width=\"600\" /\u003e\u003c/p\u003e\n\nHouse3D is a virtual 3D environment which consists of thousands of indoor scenes equipped with\na diverse set of scene types, layouts and objects sourced from the [SUNCG dataset](https://arxiv.org/abs/1611.08974).\nIt consists of over 45k indoor 3D scenes, ranging from studios to two-storied houses\nwith swimming pools and fitness rooms. All 3D objects are fully annotated with category labels.\nAgents in the environment have access to observations of multiple modalities, including RGB images,\ndepth, segmentation masks and top-down 2D map views. The renderer runs at\nthousands frames per second, making it suitable for large-scale RL training.\n\nUsage instructions can be found at [INSTRUCTION.md](INSTRUCTION.md)\n\n## Existing Research Projects with House3D\n### A. RoomNav ([paper](https://arxiv.org/abs/1801.02209))\n\n*Yi Wu, Yuxin Wu, Georgia Gkioxari, Yuandong Tian*\n\nIn this work we introduce a concept learning task, RoomNav, where an agent is asked to navigate to a destination specified by a high-level concept, e.g. `dining room`.\nWe demonstrated two neural models: a gated-CNN and a gated-LSTM, which effectively improve the agent's sensitivity to different concepts.\nFor evaluation, we emphasize on generalization ability and show that our agent can __generalize across environments__\ndue to the diverse and large-scale dataset.\n\u003cp align=\"center\"\u003e\n\u003cimg src=\"https://user-images.githubusercontent.com/1381301/33511103-ff5a71b4-d6c9-11e7-8f6d-95cc42e5b4e0.gif\" align=\"middle\" width=\"800\" /\u003e\n\u003c/p\u003e\n\n### B. Embodied QA ([project page](http://embodiedqa.org/) | [EQA paper](https://arxiv.org/abs/1711.11543) | [NMC paper](https://arxiv.org/abs/1810.11181))\n\n*Abhishek Das, Samyak Datta, Georgia Gkioxari, Stefan Lee, Devi Parikh, Dhruv Batra*\n\nEmbodied Question Answering is a new AI task where an agent is spawned at a random location in a 3D environment and asked a natural language question (\"What color is the car?\").\nIn order to answer, the agent must first intelligently navigate to explore the environment, gather information through first-person (egocentric) vision, and then answer the question (\"orange\").\n\n\u003cp align=\"center\"\u003e\n\u003cimg src=\"https://user-images.githubusercontent.com/1381301/33509618-f77bf844-d6b7-11e7-850a-b10ba6ef4a68.gif\" align=\"middle\" width=\"800\" /\u003e\n\u003c/p\u003e\n\n## Citation\n\nIf you use our platform in your research, you can cite us with:\n```\n@article{wu2018building,\n  title={Building generalizable agents with a realistic and rich 3D environment},\n  author={Wu, Yi and Wu, Yuxin and Gkioxari, Georgia and Tian, Yuandong},\n  journal={arXiv preprint arXiv:1801.02209},\n  year={2018}\n}\n```\n\n## License\n\nHouse3D is released under the [Apache 2.0 license](LICENSE).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffacebookresearch%2Fhouse3d","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffacebookresearch%2Fhouse3d","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffacebookresearch%2Fhouse3d/lists"}