{"id":13563425,"url":"https://github.com/AlgoHunt/VQRF","last_synced_at":"2025-04-03T20:30:53.431Z","repository":{"id":64132537,"uuid":"565632877","full_name":"AlgoHunt/VQRF","owner":"AlgoHunt","description":"Official implementation of our CVPR 2023 paper \"Compressing Volumetric Radiance Fields to 1 MB\"","archived":false,"fork":false,"pushed_at":"2023-07-24T09:19:36.000Z","size":595,"stargazers_count":315,"open_issues_count":2,"forks_count":19,"subscribers_count":11,"default_branch":"master","last_synced_at":"2024-08-01T13:29:14.767Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AlgoHunt.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2022-11-14T01:23:42.000Z","updated_at":"2024-06-24T08:30:09.000Z","dependencies_parsed_at":"2024-01-14T03:49:01.547Z","dependency_job_id":"4ae924ab-53a6-4f6a-b37e-a46c4d64a929","html_url":"https://github.com/AlgoHunt/VQRF","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/AlgoHunt%2FVQRF","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AlgoHunt%2FVQRF/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AlgoHunt%2FVQRF/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AlgoHunt%2FVQRF/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AlgoHunt","download_url":"https://codeload.github.com/AlgoHunt/VQRF/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":223030540,"owners_count":17076448,"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":"2024-08-01T13:01:19.096Z","updated_at":"2024-11-04T16:30:39.503Z","avatar_url":"https://github.com/AlgoHunt.png","language":"Python","readme":"# Compressing Volumetric Radiance Fields to 1 MB (CVPR2023)\n\n\u003ca href=\"https://arxiv.org/abs/2211.16386\"\u003e\u003cimg src=\"https://img.shields.io/badge/arXiv-2211.16386-b31b1b.svg\" height=22.5\u003e\u003c/a\u003e\n\nLingzhi Li*, Zhen Shen*, Zhongshu Wang, Li Shen, Liefeng Bo\n\nAlibaba Group\n\n:+1:**Update**: We Released [VQ-TensoRF](https://github.com/Spark001/VQ-TensoRF)  :+1:\n\nCitation:\n```\n@inproceedings{li2023compressing,\n  title={Compressing volumetric radiance fields to 1 mb},\n  author={Li, Lingzhi and Shen, Zhen and Wang, Zhongshu and Shen, Li and Bo, Liefeng},\n  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},\n  pages={4222--4231},\n  year={2023}\n}\n```\n\n![compression](figures/teaser.png)\n\n![Pipeline](figures/pipeline.png)\n\n**Note**: This repository only contain VQ-DVGO.\n\n\n## Setup\n\n- Download datasets:\n        [NeRF](https://drive.google.com/drive/folders/128yBriW1IG_3NJ5Rp7APSTZsJqdJdfc1)\n        [NSVF](https://dl.fbaipublicfiles.com/nsvf/dataset/Synthetic_NSVF.zip),  [T\u0026T (masked)](https://dl.fbaipublicfiles.com/nsvf/dataset/TanksAndTemple.zip)\n\n\n- Install required libraries\n```\npip install -r requirements.txt\ncd lib/cuda\npython setup.py install\n```\n\nPlease  install the correct version of [Pytorch](https://pytorch.org/) and [torch_scatter](https://github.com/rusty1s/pytorch_scatter) for your machine.\n\n## Directory structure for the datasets\n\n\u003c!-- \u003cdetails\u003e\n  \u003csummary\u003e (click to expand;) \u003c/summary\u003e --\u003e\n```\ndata\n├── nerf_synthetic     # Link: https://drive.google.com/drive/folders/128yBriW1IG_3NJ5Rp7APSTZsJqdJdfc1\n│   └── [chair|drums|ficus|hotdog|lego|materials|mic|ship]\n│       ├── [train|val|test]\n│       │   └── r_*.png\n│       └── transforms_[train|val|test].json\n│\n├── Synthetic_NSVF     # Link: https://dl.fbaipublicfiles.com/nsvf/dataset/Synthetic_NSVF.zip\n│   └── [Bike|Lifestyle|Palace|Robot|Spaceship|Steamtrain|Toad|Wineholder]\n│       ├── intrinsics.txt\n│       ├── rgb\n│       │   └── [0_train|1_val|2_test]_*.png\n│       └── pose\n│           └── [0_train|1_val|2_test]_*.txt\n│\n│\n└── TanksAndTemple     # Link: https://dl.fbaipublicfiles.com/nsvf/dataset/TanksAndTemple.zip\n    └── [Barn|Caterpillar|Family|Ignatius|Truck]\n        ├── intrinsics.txt\n        ├── rgb\n        │   └── [0|1|2]_*.png\n        └── pose\n            └── [0|1|2]_*.txt\n    \n```\n\n\n\u003c!-- \u003c/details\u003e --\u003e\n\n## Training\n\n```\n# for nerf_synthetic datasets\npython autotask_final.py -g \"0 1 2 3 4 5 6 7\"  --configname syn_4096code \n\n# for Synthetic_NSVF datasets\npython autotask_final.py -g \"0 1 2 3 4 5 6 7\"  --configname nsvf_4096code --dataset nsvf\n\n# for TanksAndTemple datasets\npython autotask_final.py -g \"0 1 2 3 4 5 6 7\"  --configname tnt_4096code  --dataset tnt\n```\n\nFixing TanksandTemples dataset following this [issue](https://github.com/sunset1995/DirectVoxGO/issues/4)\n\nSet `-g` option according to the availible gpu on your machine. \n\n## Testing \n\n```\n# for nerf_synthetic datasets\npython autotask_eval_only.py -g \"0 1 2 3 4 5 6 7\"  --configname syn_4096code \n\n# for Synthetic_NSVF datasets\npython autotask_eval_only.py -g \"0 1 2 3 4 5 6 7\"  --configname nsvf_4096code --dataset nsvf\n\n# for TanksAndTemple datasets\npython autotask_eval_only.py -g \"0 1 2 3 4 5 6 7\"  --configname tnt_4096code  --dataset tnt\n```\n","funding_links":[],"categories":["Python","🔧 **Utility Frameworks \u0026 Tools**"],"sub_categories":["🎬 **VQRF** - Video Compression"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FAlgoHunt%2FVQRF","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FAlgoHunt%2FVQRF","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FAlgoHunt%2FVQRF/lists"}