{"id":18614440,"url":"https://github.com/kaist-ami/HDR-Plenoxels","last_synced_at":"2025-04-11T00:30:48.043Z","repository":{"id":46867494,"uuid":"515211830","full_name":"kaist-ami/HDR-Plenoxels","owner":"kaist-ami","description":"[ECCV'22] Official PyTorch Implementation of \"HDR-Plenoxels: Self-Calibrating High Dynamic Range Radiance Fields\"","archived":false,"fork":false,"pushed_at":"2024-02-24T14:42:01.000Z","size":7425,"stargazers_count":111,"open_issues_count":4,"forks_count":10,"subscribers_count":5,"default_branch":"main","last_synced_at":"2025-03-14T02:43:59.761Z","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":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/kaist-ami.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":"2022-07-18T14:10:39.000Z","updated_at":"2024-08-21T12:23:48.000Z","dependencies_parsed_at":"2024-02-24T15:45:13.135Z","dependency_job_id":null,"html_url":"https://github.com/kaist-ami/HDR-Plenoxels","commit_stats":null,"previous_names":["kaist-ami/hdr-plenoxels"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kaist-ami%2FHDR-Plenoxels","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kaist-ami%2FHDR-Plenoxels/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kaist-ami%2FHDR-Plenoxels/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kaist-ami%2FHDR-Plenoxels/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kaist-ami","download_url":"https://codeload.github.com/kaist-ami/HDR-Plenoxels/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":"2024-11-07T03:25:56.692Z","updated_at":"2025-04-11T00:30:43.024Z","avatar_url":"https://github.com/kaist-ami.png","language":"Python","funding_links":[],"categories":["Papers"],"sub_categories":["NeRF Related Tasks"],"readme":"# HDR-Plenoxels (ECCV 2022)\n\n### [Paper](https://arxiv.org/abs/2208.06787) | [Project Page](https://hdr-plenoxels.github.io/)\n\nThis repository is official implementation for the ECCV 2022 paper, [HDR-Plenoxels: Self-Calibrating High Dynamic Range Radiance Fields](https://arxiv.org/abs/2208.06787). \n\nHDR-Plenoxels is end-to-end HDR radiance fields learning method w/ only LDR images of the varying camera and w/o additional camera information (e.g., exposure value).\nWe deign the tone-mapping module based on a physical camera pipeline.\nWe also deploy a multi-view dataset containing varying camera conditions.\n\nhttps://user-images.githubusercontent.com/38632805/197250380-5048a4a4-f462-46ee-acf6-f1d4cf848795.mov\n\n## Setup\n\nThis code is based on [Plenoxels](https://github.com/sxyu/svox2) official implementation. \nYou have to follow setup detail of Plenoxels repository (below).\n\n\nFirst create the virtualenv; we recommend using conda:\n```sh\nconda env create -f environment.yml\nconda activate plenoxel\n```\n\nThen clone the repo and install the library at the root (svox2), which includes a CUDA extension.\n\nIf your CUDA toolkit is older than 11, then you will need to install CUB as follows:\n`conda install -c bottler nvidiacub`.\nSince CUDA 11, CUB is shipped with the toolkit.\n\nTo install the main library, simply run\n```\npip install .\n```\nIn the repo root directory.\n\n## Prepare Datasets\n\nWe deploy our HDR training dataset for LLFF format, and the dataset will be auto-detected.\n\n\nPlease get the synthetic and real LLFF datasets from [this link](\u003chttps://postechackr-my.sharepoint.com/personal/gucka28_postech_ac_kr/_layouts/15/onedrive.aspx?id=%2Fpersonal%2Fgucka28%5Fpostech%5Fac%5Fkr%2FDocuments%2FHDR%2DPlenoxels%5Fdataset\u0026ga=1\u003e).\n\n\n## Voxel Optimization (Training)\n\nFor training a single scene, see `opt/hdr_opt.py`.\n\nYou can train both of our synthetic and real HDR datasets.\nInside `opt/`, run below shell scripts.\n\nIf you want to use synthetic datset, run below shell scripts.\n```bash\n# Plenoxels + static dataset\n./shell/syn/train_mid.sh\n\n# Plenoxels + varying datset\n./shell/syn/train_mix.sh\n\n# HDR-Plenoxes + varying datset\n./shell/syn/train_tone.sh\n```\n\nIf you want to use real datset, run below shell scripts.\n```bash\n# Plenoxels + static dataset\n./shell/real/train_mid.sh\n\n# Plenoxels + varying datset\n./shell/real/train_mix.sh\n\n# HDR-Plenoxes + varying datset\n./shell/real/train_tone.sh\n```\n\nWe do not provide pretrained checkpoints.\n\n## Evaluation\n\n- Use `opt/shell/render/render_hdr.sh` for rendering HDR radiance fields.\n\n- Use `opt/shell/render/render_ldr.sh` for rendering LDR radiance fields which is final output.\n\n- If you don't want to save all frames, which is very slow, add `--no_imsave` to avoid this.\n\n## Metric\n\nInside opt/, run\n```bash\nCUDA_VISIBLE_DEVICES=0 python hdr_calc_metrics.py\n```\n\n- You can get PSNR, SSIM, and LPIPS scores for right-half novel views.\n\n## Citation\n\n```BibTeX\n@inproceedings{jun2022hdr,\n    title     = {HDR-Plenoxels: Self-Calibrating High Dynamic Range Radiance Fields},\n    author    = {Jun-Seong, Kim and Yu-Ji, Kim and Ye-Bin, Moon and Oh, Tae-Hyun},\n    booktitle = {ECCV},\n    year      = {2022},\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkaist-ami%2FHDR-Plenoxels","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkaist-ami%2FHDR-Plenoxels","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkaist-ami%2FHDR-Plenoxels/lists"}