{"id":18614375,"url":"https://github.com/dvlab-research/EfficientNeRF","last_synced_at":"2025-04-11T00:30:35.172Z","repository":{"id":37425050,"uuid":"473989358","full_name":"dvlab-research/EfficientNeRF","owner":"dvlab-research","description":"The official code for \"Efficient Neural Radiance Fields\" in CVPR2022.","archived":false,"fork":false,"pushed_at":"2022-07-13T13:00:29.000Z","size":44,"stargazers_count":153,"open_issues_count":7,"forks_count":11,"subscribers_count":11,"default_branch":"main","last_synced_at":"2024-11-07T03:31:10.398Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/dvlab-research.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}},"created_at":"2022-03-25T11:51:10.000Z","updated_at":"2024-09-16T09:44:36.000Z","dependencies_parsed_at":"2022-08-09T09:15:36.585Z","dependency_job_id":null,"html_url":"https://github.com/dvlab-research/EfficientNeRF","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/dvlab-research%2FEfficientNeRF","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dvlab-research%2FEfficientNeRF/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dvlab-research%2FEfficientNeRF/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dvlab-research%2FEfficientNeRF/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dvlab-research","download_url":"https://codeload.github.com/dvlab-research/EfficientNeRF/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248322208,"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":"2024-11-07T03:25:55.643Z","updated_at":"2025-04-11T00:30:34.831Z","avatar_url":"https://github.com/dvlab-research.png","language":"Python","funding_links":[],"categories":["Papers"],"sub_categories":["NeRF"],"readme":"## The official code for \"[EfficientNeRF: Efficient Neural Radiance Fields](https://arxiv.org/abs/2206.00878)\" in CVPR2022.\n\n### Environment (Tested)\n- Ubuntu 18.04\n- Python 3.7\n- CUDA 11.x\n- Pytorch 1.9.1\n- Pytorch-Lightning 1.6.4\n\n### Install via Anaconda\n```\n$ conda create -n EfficientNeRF python=3.8\n$ conda activate EfficientNeRF\n$ pip install torch==1.9.1+cu111 torchvision==0.10.1+cu111 torchaudio==0.9.1 -f https://download.pytorch.org/whl/torch_stable.html\n$ pip install -r requirements.txt\n```\n\n### Training\n```\n$ DATA_DIR=/path/to/lego\n$ python train.py \\\n   --dataset_name blender \\\n   --root_dir $DATA_DIR \\\n   --N_samples 128 \\\n   --N_importance 5 --img_wh 800 800 \\\n   --num_epochs 16 --batch_size 4096 \\\n   --optimizer radam --lr 2e-3 \\\n   --lr_scheduler poly \\\n   --coord_scope 3.0 \\\n   --warmup_step 5000\\\n   --sigma_init 30.0 \\\n   --weight_threashold 1e-5 \\\n   --exp_name lego_coarse128_fine5_V384\n```\n\n### Visualization\n```\n$ tensorboard --logdir=./logs\n```\n\n### Question\n- Q1. Different hyperparameters from the original paper\n* A1. There are many combinations between these hyperparameters. You are free to balance the training speed and accuracy by modify them. \n- Q2. When will NeRF-Tree released?\n* A2. Hard to say a specific date. The data structure NeRF-Tree is closed to Octree.\n\n### Progress\nMore scenes and applications will be suported soon. Stay tune!\n\n### Acknowledgement\nOur initial code was borrowed from \n- [nerf-pl:https://github.com/kwea123/nerf_pl](https://github.com/kwea123/nerf_pl)\n\n### Citation\nIf you find our code or paper helps, please cite our paper:\n```\n@InProceedings{Hu_2022_CVPR,\n    author    = {Hu, Tao and Liu, Shu and Chen, Yilun and Shen, Tiancheng and Jia, Jiaya},\n    title     = {EfficientNeRF  Efficient Neural Radiance Fields},\n    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},\n    month     = {June},\n    year      = {2022},\n    pages     = {12902-12911}\n}\n```\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdvlab-research%2FEfficientNeRF","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdvlab-research%2FEfficientNeRF","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdvlab-research%2FEfficientNeRF/lists"}