{"id":18614490,"url":"https://github.com/albertpumarola/D-NeRF","last_synced_at":"2025-04-11T00:30:50.919Z","repository":{"id":43599255,"uuid":"339154219","full_name":"albertpumarola/D-NeRF","owner":"albertpumarola","description":null,"archived":false,"fork":false,"pushed_at":"2024-01-26T03:09:49.000Z","size":2429,"stargazers_count":535,"open_issues_count":16,"forks_count":67,"subscribers_count":8,"default_branch":"main","last_synced_at":"2024-11-07T03:31:47.473Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","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/albertpumarola.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,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2021-02-15T17:27:39.000Z","updated_at":"2024-10-21T00:20:29.000Z","dependencies_parsed_at":"2024-01-22T10:58:51.326Z","dependency_job_id":"58b177c8-101e-470c-a5da-4e02de006e61","html_url":"https://github.com/albertpumarola/D-NeRF","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/albertpumarola%2FD-NeRF","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/albertpumarola%2FD-NeRF/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/albertpumarola%2FD-NeRF/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/albertpumarola%2FD-NeRF/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/albertpumarola","download_url":"https://codeload.github.com/albertpumarola/D-NeRF/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248322220,"owners_count":21084333,"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":"2024-11-07T03:25:57.776Z","updated_at":"2025-04-11T00:30:47.035Z","avatar_url":"https://github.com/albertpumarola.png","language":"Jupyter Notebook","funding_links":[],"categories":["Papers"],"sub_categories":["NeRF Related Tasks"],"readme":"\u003cimg src='https://www.albertpumarola.com/images/2021/D-NeRF/teaser2.gif' align=\"right\" width=400\u003e\n\n# D-NeRF: Neural Radiance Fields for Dynamic Scenes\n### [[Project]](https://www.albertpumarola.com/research/D-NeRF/index.html)[ [Paper]](https://openaccess.thecvf.com/content/CVPR2021/papers/Pumarola_D-NeRF_Neural_Radiance_Fields_for_Dynamic_Scenes_CVPR_2021_paper.pdf) \n\n[D-NeRF](https://www.albertpumarola.com/research/D-NeRF/index.html) is a method for synthesizing novel views, at an arbitrary point in time, of dynamic scenes with complex non-rigid geometries. We optimize an underlying deformable volumetric function from a sparse set of input monocular views without the need of ground-truth geometry nor multi-view images.\n\nThis project is an extension of [NeRF](http://www.matthewtancik.com/nerf) enabling it to model dynmaic scenes. The code heavily relays on [NeRF-pytorch](https://github.com/yenchenlin/nerf-pytorch). \n\n![D-NeRF](https://www.albertpumarola.com/images/2021/D-NeRF/model.png)\n\n## Installation\n```\ngit clone https://github.com/albertpumarola/D-NeRF.git\ncd D-NeRF\nconda create -n dnerf python=3.6\nconda activate dnerf\npip install -r requirements.txt\ncd torchsearchsorted\npip install .\ncd ..\n```\n\n## Download Pre-trained Weights\n You can download the pre-trained models from [drive](https://drive.google.com/file/d/1uHVyApwqugXTFuIRRlE4abTW8_rrVeIK/view?usp=sharing) or [dropbox](https://www.dropbox.com/s/25sveotbx2x7wap/logs.zip?dl=0). Unzip the downloaded data to the project root dir in order to test it later. See the following directory structure for an example:\n```\n├── logs \n│   ├── mutant\n│   ├── standup \n│   ├── ...\n```\n\n## Download Dataset\n You can download the datasets from [drive](https://drive.google.com/file/d/19Na95wk0uikquivC7uKWVqllmTx-mBHt/view?usp=sharing) or [dropbox](https://www.dropbox.com/s/0bf6fl0ye2vz3vr/data.zip?dl=0). Unzip the downloaded data to the project root dir in order to train. See the following directory structure for an example:\n```\n├── data \n│   ├── mutant\n│   ├── standup \n│   ├── ...\n```\n\n## Demo\nWe provide simple jupyter notebooks to explore the model. To use them first download the pre-trained weights and dataset.\n\n| Description      | Jupyter Notebook |\n| ----------- | ----------- |\n| Synthesize novel views at an arbitrary point in time. | render.ipynb|\n| Reconstruct mesh at an arbitrary point in time. | reconstruct.ipynb|\n| Quantitatively evaluate trained model. | metrics.ipynb|\n\n## Test\nFirst download pre-trained weights and dataset. Then, \n```\npython run_dnerf.py --config configs/mutant.txt --render_only --render_test\n```\nThis command will run the `mutant` experiment. When finished, results are saved to `./logs/mutant/renderonly_test_799999` To quantitatively evaluate model run `metrics.ipynb` notebook\n\n## Train\nFirst download the dataset. Then,\n```\nconda activate dnerf\nexport PYTHONPATH='path/to/D-NeRF'\nexport CUDA_VISIBLE_DEVICES=0\npython run_dnerf.py --config configs/mutant.txt\n```\n\n## Citation\nIf you use this code or ideas from the paper for your research, please cite our paper:\n```\n@article{pumarola2020d,\n  title={D-NeRF: Neural Radiance Fields for Dynamic Scenes},\n  author={Pumarola, Albert and Corona, Enric and Pons-Moll, Gerard and Moreno-Noguer, Francesc},\n  journal={arXiv preprint arXiv:2011.13961},\n  year={2020}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falbertpumarola%2FD-NeRF","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Falbertpumarola%2FD-NeRF","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falbertpumarola%2FD-NeRF/lists"}