{"id":19999876,"url":"https://github.com/eliphatfs/zerorf","last_synced_at":"2026-03-03T21:01:27.190Z","repository":{"id":212576787,"uuid":"731419913","full_name":"eliphatfs/zerorf","owner":"eliphatfs","description":"ZeroRF: Fast Sparse View 360° Reconstruction with Zero Pretraining","archived":false,"fork":false,"pushed_at":"2024-04-22T22:46:56.000Z","size":494,"stargazers_count":197,"open_issues_count":0,"forks_count":14,"subscribers_count":8,"default_branch":"main","last_synced_at":"2025-10-07T05:46:50.040Z","etag":null,"topics":["3d-aigc","3d-reconstruction","nerf","paper-implementations"],"latest_commit_sha":null,"homepage":"https://sarahweiii.github.io/zerorf/","language":"Python","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/eliphatfs.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":"2023-12-14T03:29:28.000Z","updated_at":"2025-10-04T14:24:15.000Z","dependencies_parsed_at":"2023-12-15T03:25:03.360Z","dependency_job_id":"340e4d0d-69ce-4712-8ed1-dc7f34c561c5","html_url":"https://github.com/eliphatfs/zerorf","commit_stats":null,"previous_names":["eliphatfs/zerorf"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/eliphatfs/zerorf","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eliphatfs%2Fzerorf","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eliphatfs%2Fzerorf/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eliphatfs%2Fzerorf/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eliphatfs%2Fzerorf/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/eliphatfs","download_url":"https://codeload.github.com/eliphatfs/zerorf/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eliphatfs%2Fzerorf/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30060626,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-03T18:21:05.932Z","status":"ssl_error","status_checked_at":"2026-03-03T18:20:59.341Z","response_time":61,"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":["3d-aigc","3d-reconstruction","nerf","paper-implementations"],"created_at":"2024-11-13T05:13:14.193Z","updated_at":"2026-03-03T21:01:27.171Z","avatar_url":"https://github.com/eliphatfs.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ZeroRF: Sparse View 360° Reconstruction with Zero Pretraining [CVPR 2024]\n\n[\\[Project Page\\]](https://sarahweiii.github.io/zerorf/)\n[\\[Paper\\]](http://arxiv.org/abs/2312.09249)\n\n## Requirements\n\nAs the code is based on [the SSDNeRF codebase](https://github.com/Lakonik/SSDNeRF), the requirements are the same. Additionally, we provide a docker image for ease of use.\n\n### Install via Docker\n\n```bash\ndocker pull eliphatfs/zerorf-ssdnerf:0.0.2\n```\n\n### Install Manually (Copied from SSDNeRF)\n\nThe code has been tested in the environment described as follows:\n\n- Linux (tested on Ubuntu 18.04/20.04 LTS)\n- Python 3.7\n- [CUDA Toolkit](https://developer.nvidia.com/cuda-toolkit-archive) 11\n- [PyTorch](https://pytorch.org/get-started/previous-versions/) 1.12.1\n- [MMCV](https://github.com/open-mmlab/mmcv) 1.6.0\n- [MMGeneration](https://github.com/open-mmlab/mmgeneration) 0.7.2\n- [SpConv](https://github.com/traveller59/spconv) 2.3.6\n\nOther dependencies can be installed via `pip install -r requirements.txt`. \n\nAn example of commands for installing the Python packages is shown below (you may change the CUDA version yourself):\n\n```bash\n# Export the PATH of CUDA toolkit\nexport PATH=/usr/local/cuda-11.5/bin:$PATH\nexport LD_LIBRARY_PATH=/usr/local/cuda-11.5/lib64:$LD_LIBRARY_PATH\n\n# Create conda environment\nconda create -y -n ssdnerf python=3.7\nconda activate ssdnerf\n\n# Install PyTorch\nconda install pytorch==1.12.1 torchvision==0.13.1 torchaudio==0.12.1 cudatoolkit=11.3 -c pytorch\n\n# Install MMCV and MMGeneration\npip install -U openmim\nmim install mmcv-full==1.6\ngit clone https://github.com/open-mmlab/mmgeneration \u0026\u0026 cd mmgeneration \u0026\u0026 git checkout v0.7.2\npip install -v -e .\ncd ..\n\n# Install SpConv\npip install spconv-cu114\n\n# Clone this repo and install other dependencies\ngit clone \u003cthis repo\u003e \u0026\u0026 cd \u003crepo folder\u003e \u0026\u0026 git checkout ssdnerf-sd\npip install -r requirements.txt\n```\n\nOptionally, you can install [xFormers](https://github.com/facebookresearch/xformers) for efficnt attention. Also, this codebase should be able to work on Windows systems as well (tested in the inference mode).\n\nLastly, there are two CUDA packages from [torch-ngp](https://github.com/ashawkey/torch-ngp) that need to be built locally if you install dependencies manually.\n\n```bash\ncd lib/ops/raymarching/\npip install -e .\ncd ../shencoder/\npip install -e .\ncd ../../..\n```\n\n## Running\n\nExecute `zerorf.py` to run ZeroRF.\n\n**Zero123++ Image**\n\nZeroRF can be used to perform reconstruction on generated multi-view images to perform 3D content generation.\nYou need to prepare a segmented RGBA image in Zero123++ format (see https://github.com/SUDO-AI-3D/zero123plus).\nAn example can be found at `examples/ice.png`.\n\n```bash\npython zerorf.py --load-image=examples/ice.png\n```\n\nThe default setup requires 10GB VRAM to operate.\n\n**NeRF-Synthetic**\n\nTo run general reconstruction, you can prepare the dataset in NeRF-Synthetic format.\nThe NeRF-Synthetic dataset itself can be obtained [here](https://drive.google.com/drive/folders/1JDdLGDruGNXWnM1eqY1FNL9PlStjaKWi).\n\n```bash\npython zerorf.py --rep=tensorf --data-dir=path/to/nerf_synthetic --obj=hotdog --n-views=6 --dataset=nerf_syn\n```\n\n**Open-Illumination**\n\nThe dataset can be obtained [here](https://oppo-us-research.github.io/OpenIllumination/). \nWe use the camera aligned with axes ([train_split](https://huggingface.co/datasets/OpenIllumination/OpenIllumination/raw/main/others/transforms_alignz_train.json), [test_split](https://huggingface.co/datasets/OpenIllumination/OpenIllumination/raw/main/others/transforms_alignz_train.json)), please put the two files under `path/to/open_illumination/lighting_patterns`.\n\n```bash\npython zerorf.py --rep=tensorf --data-dir=path/to/open_illumination/lighting_patterns --obj=obj_04_stone --n-views=6 --dataset=oi\n```\n\nThe default setup requires about 16GB VRAM to operate depending on the object.\nYou may want to adjust the `--n-rays-up` parameter to a lower value so it fits your VRAM (convergence could take more steps and longer time).\n\n**Configuration**\n\nYou can find more configurations in `opt.py`.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feliphatfs%2Fzerorf","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Feliphatfs%2Fzerorf","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feliphatfs%2Fzerorf/lists"}