{"id":33210066,"url":"https://zju3dv.github.io/object_nerf/","last_synced_at":"2025-11-21T05:01:51.188Z","repository":{"id":43107973,"uuid":"401274525","full_name":"zju3dv/object_nerf","owner":"zju3dv","description":"Code for \"Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering\", ICCV 2021","archived":false,"fork":false,"pushed_at":"2023-11-07T02:37:41.000Z","size":7088,"stargazers_count":313,"open_issues_count":13,"forks_count":22,"subscribers_count":29,"default_branch":"main","last_synced_at":"2025-05-20T00:07:33.815Z","etag":null,"topics":["3d-reconstruction","3d-vision","nerf"],"latest_commit_sha":null,"homepage":"https://zju3dv.github.io/object_nerf/","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/zju3dv.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2021-08-30T08:43:00.000Z","updated_at":"2024-12-16T07:31:00.000Z","dependencies_parsed_at":"2024-01-18T18:25:29.888Z","dependency_job_id":"72aafb3d-b964-4e05-8424-d2813d6a86d1","html_url":"https://github.com/zju3dv/object_nerf","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/zju3dv/object_nerf","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zju3dv%2Fobject_nerf","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zju3dv%2Fobject_nerf/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zju3dv%2Fobject_nerf/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zju3dv%2Fobject_nerf/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zju3dv","download_url":"https://codeload.github.com/zju3dv/object_nerf/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zju3dv%2Fobject_nerf/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":285560043,"owners_count":27192467,"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":"2025-11-21T02:00:06.175Z","response_time":61,"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":["3d-reconstruction","3d-vision","nerf"],"created_at":"2025-11-16T11:00:26.468Z","updated_at":"2025-11-21T05:01:51.183Z","avatar_url":"https://github.com/zju3dv.png","language":"Python","funding_links":[],"categories":["Papers","Modeling, Sculpting \u0026 Texturing"],"sub_categories":["Material Creation Tools"],"readme":"# Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering\n### [Project Page](https://zju3dv.github.io/object_nerf) | [Video](https://www.youtube.com/watch?v=VTEROu-Yz04) | [Paper](http://www.cad.zju.edu.cn/home/gfzhang/papers/object_nerf/object_nerf.pdf)\n\n\u003cdiv align=center\u003e\n\u003cimg src=\"assets/teaser.gif\" width=\"100%\"/\u003e\n\u003c/div\u003e\n\n\u003e [Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering](http://www.cad.zju.edu.cn/home/gfzhang/papers/object_nerf/object_nerf.pdf)  \n\u003e Bangbang Yang, Yinda Zhang, Yinghao Xu, Yijin Li, Han Zhou, Hujun Bao, Guofeng Zhang, Zhaopeng Cui.  \n\u003e ICCV 2021\n\n\n## Installation\n\nWe have tested the code on pytorch 1.8.1, while a newer version of pytorch should also work.\n\n```bash\nconda create -n object_nerf python=3.8\nconda activate object_nerf\nconda install pytorch==1.8.1 torchvision cudatoolkit=11.1 -c pytorch -c conda-forge\npip install -r requirements.txt\n```\n\n## Data Preparation\n\nPlease go to the [data preparation][1].\n\n## Training\n\nYou can run `train.py` to train the model, and here are two examples.\n\n```bash\n# train on ScanNet 0113\npython train.py dataset_config=config/scannet_base_0113_multi.yml \"img_wh=[640,480]\" exp_name=my_expr_scannet_0113\n\n# train on ToyDesk 2\npython train.py dataset_config=config/toy_desk_2.yml \"img_wh=[640,480]\" exp_name=my_expr_toydesk_2\n```\n\n## Editable Scene Rendering\n\nHere we provide two examples of scene editing with pre-trained models ([download link](https://www.dropbox.com/scl/fi/kz5r1y3pct8uvzmog22hl/object_nerf_edit_demo_models.zip?rlkey=e06i0y3m3uwocnxk0wrf10m62\u0026dl=0)).\n\n### ScanNet Object Duplicating and Moving\n\n```bash\npython test/demo_editable_render.py \\\n    config=test/config/edit_scannet_0113.yaml \\\n    ckpt_path=../object_nerf_edit_demo_models/scannet_0113/last.ckpt \\\n    prefix=scannet_0113_duplicating_moving\n```\n\n### ToyDesk Object Rotating\n\n```bash\npython test/demo_editable_render.py \\\n    config=test/config/edit_toy_desk_2.yaml \\\n    ckpt_path=../object_nerf_edit_demo_models/toydesk_2/last.ckpt \\\n    prefix=toy_desk2_rotating\n```\n\nRemember to change the `ckpt_path` to the uncompressed model checkpoint file.\n\nYou can find the rendered image in `debug/rendered_view/render_xxxxxx_scannet_0113_duplicating_moving` or `debug/rendered_view/render_xxxxxx_toy_desk2_rotating` which should look as follows:\n\n\u003cdiv align=center\u003e\n\u003cimg src=\"assets/scannet_0113_dup_move.gif\" width=\"30%\"/\u003e\n\u0026nbsp\u0026nbsp\u0026nbsp\u0026nbsp\n\u003cimg src=\"assets/toydesk_rot.gif\" width=\"30%\"/\u003e\n\u003c/div\u003e\n\n\u003c!-- \u003cdiv align=center\u003e\n\u003cimg src=\"assets/toydesk_rot.gif\" width=\"30%\"/\u003e\n\u003c/div\u003e --\u003e\n\n## Citation\n\nIf you find this work useful, please consider citing:\n\n```\n@inproceedings{yang2021objectnerf,\n    title={Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering},\n    author={Yang, Bangbang and Zhang, Yinda and Xu, Yinghao and Li, Yijin and Zhou, Han and Bao, Hujun and Zhang, Guofeng and Cui, Zhaopeng},\n    booktitle = {International Conference on Computer Vision ({ICCV})},\n    month = {October},\n    year = {2021},\n}\n```\n\n\n## Acknowledgement\n\nIn this project we use (parts of) the implementations of the following works:\n\n- [nerf_pl](https://github.com/kwea123/nerf_pl/) by kwea123.\n- [nerf_pytorch](https://github.com/yenchenlin/nerf-pytorch) by Yen-Chen Lin.\n- [scannet](https://github.com/ScanNet/ScanNet) by Angela Dai.\n\nWe thank the respective authors for open sourcing their methods. \n\n[1]: ./data_preparation/\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/zju3dv.github.io%2Fobject_nerf%2F","html_url":"https://awesome.ecosyste.ms/projects/zju3dv.github.io%2Fobject_nerf%2F","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/zju3dv.github.io%2Fobject_nerf%2F/lists"}