{"id":19984498,"url":"https://github.com/intellabs/clnerf","last_synced_at":"2025-03-16T09:09:13.043Z","repository":{"id":190729932,"uuid":"678545894","full_name":"IntelLabs/CLNeRF","owner":"IntelLabs","description":null,"archived":false,"fork":false,"pushed_at":"2024-09-11T16:11:15.000Z","size":5128,"stargazers_count":67,"open_issues_count":3,"forks_count":10,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-03-03T02:45:16.408Z","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":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/IntelLabs.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":"2023-08-14T20:02:06.000Z","updated_at":"2025-02-19T08:01:56.000Z","dependencies_parsed_at":"2024-09-11T23:06:12.987Z","dependency_job_id":"435f12ea-dd6d-4e1f-9aec-721e904a51fc","html_url":"https://github.com/IntelLabs/CLNeRF","commit_stats":null,"previous_names":["intellabs/clnerf"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/IntelLabs%2FCLNeRF","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/IntelLabs%2FCLNeRF/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/IntelLabs%2FCLNeRF/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/IntelLabs%2FCLNeRF/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/IntelLabs","download_url":"https://codeload.github.com/IntelLabs/CLNeRF/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243847062,"owners_count":20357317,"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":"2024-11-13T04:19:12.713Z","updated_at":"2025-03-16T09:09:13.011Z","avatar_url":"https://github.com/IntelLabs.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# CLNeRF\nOfficial implementation of 'CLNeRF: Continual Learning Meets NeRF' (accepted to ICCV'23)\n\n[[Paper](https://arxiv.org/abs/2308.14816)] [[Video](https://youtu.be/nLRt6OoDGq0)] [[Dataset](https://huggingface.co/datasets/IntelLabs/WAT-WorldAcrossTime)]  [Web Demo (coming soon)]\n\n![Example Image](https://github.com/ZhipengCai/CLNeRF/blob/main/demo/teaser.png)\n\nWe study the problem of continual learning in the context of NeRFs. We propose a new dataset World Across Time (WAT) for this purpose, where during continual learning, the scene appearance and geometry can change over time (at different time step/task of continual learning). We propose a simple yet effective method CLNeRF which combines generative replay with advanced NeRF architectures so that a single NeRF model can efficiently adapt to gradually revealed new data, i.e., render scenes at different time with potential appearance and geometry changes, without the need to store historical images.\n\nTo facilitate future research on continual NeRF, we provide the code to run different continual learning methods on different NeRF datasets (including WAT).\n\nPlease give us a star or cite our paper if you find it useful.\n\n# Contact\nPlease contact Zhipeng Cai (homepage: https://zhipengcai.github.io/, email: czptc2h@gmail.com) if you have questions, comments or want to collaborate on this repository to make it better.\n\nWe are actively looking for good research interns, contact Zhipeng if you are interested (multiple bases are possible, e.g., US, Munich, China).\n\n```bash\n@inproceedings{iccv23clnerf,\ntitle={CLNeRF: Continual Learning Meets NeRF},\nauthor={Zhipeng Cai, Matthias Müller},\nyear={2023},\nbooktitle={ICCV},\n}\n```\n\n# Installation\n\n## Hardware\n\n* OS: Ubuntu 20.04\n* NVIDIA GPU with Compute Compatibility \u003e= 75 and memory \u003e 12GB (Tested with RTX3090 Ti and RTX6000), CUDA 11.3 (might work with older version)\n\n## Environment setup\n* Clone this repo and submodules (pycolmap): `git clone --recurse-submodules https://github.com/IntelLabs/CLNeRF.git`\n* simply run the code in `setup_env.sh` line by line (to avoid failure in specific line so that your own environment is damaged)\n\n### Docker (optional)\nFirst make sure you have [installed Docker](https://docs.docker.com/engine/install/), and cloned the repository and it's your current working directory.\n```bash\ngit clone --recursive https://github.com/IntelLabs/CLNeRF.git\ncd CLNeRF\ndocker pull joaquingajardo/clnerf:latest\ndocker run -d --name CLNeRF --gpus=all --shm-size=24g -w /workspace/CLNeRF -v ${PWD}:/workspace/CLNeRF -t joaquingajardo/clnerf:latest\ndocker exec -it CLNeRF bash\n# Optionally in vscode you can attach to the container just created for easier debugging and developing\n```\n\n## Dataset prepare (Naming follows Fig.4 of the main paper, currently support WAT, SynthNeRF and NeRF++)\n\n```bash\nbash prepare_datasets.sh\n```\n\n# Run experiments\n\n```bash\n# run experiments on CLNeRF (WAT, SynthNeRF and NeRF++ datasets are currently supported)\nbash run_CLNeRF.sh\n# run experiments on MEIL-NeRF\nbash run_MEIL.sh\n# run experiments on ER (experience replay)\nbash run_ER.sh\n# run experiments on EWC \nbash run_EWC.sh\n# run experiments on NT (naive training/finetuning on the sequential data)\nbash run_NT.sh\n# render video using CLNeRF model\nscene=breville\ntask_number=5\ntask_curr=4\nrep=10\nscale=8.0 # change to the right scale according to the corresponding training script (scripts/NT/WAT/breville.sh)\nckpt_path=/export/work/zcai/WorkSpace/CLNeRF/CLNeRF/ckpts/NGPGv2_CL/colmap_ngpa_CLNerf/${scene}_10/epoch=19-v4.ckpt # change to your ckpt path\nbash scripts/CLNeRF/WAT/render_video.sh $task_number $task_curr $scene $ckpt_path $rep $scale $render_fname\n```\n# License\n\nThis repository is under the Apache 2.0 License, it is free for non-commercial use. Please contact Zhipeng for other use cases.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fintellabs%2Fclnerf","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fintellabs%2Fclnerf","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fintellabs%2Fclnerf/lists"}