{"id":13711033,"url":"https://akshatdave.github.io/pandora/","last_synced_at":"2025-05-06T20:31:42.737Z","repository":{"id":46333098,"uuid":"515326727","full_name":"akshatdave/pandora","owner":"akshatdave","description":"Official Pytorch implementation of PANDORA: Polarization-Aided Neural Decomposition of Radiance","archived":false,"fork":false,"pushed_at":"2022-07-19T20:36:27.000Z","size":7858,"stargazers_count":62,"open_issues_count":4,"forks_count":5,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-11-13T21:44:48.228Z","etag":null,"topics":["3d-reconstruction","computer-vision","inverse-rendering","nerf","neural-rendering","polarization","polarization-imaging"],"latest_commit_sha":null,"homepage":"https://akshatdave.github.io/pandora","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/akshatdave.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":"2022-07-18T20:09:19.000Z","updated_at":"2024-10-13T09:58:19.000Z","dependencies_parsed_at":"2022-08-22T09:00:44.303Z","dependency_job_id":null,"html_url":"https://github.com/akshatdave/pandora","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/akshatdave%2Fpandora","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/akshatdave%2Fpandora/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/akshatdave%2Fpandora/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/akshatdave%2Fpandora/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/akshatdave","download_url":"https://codeload.github.com/akshatdave/pandora/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252764372,"owners_count":21800681,"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":["3d-reconstruction","computer-vision","inverse-rendering","nerf","neural-rendering","polarization","polarization-imaging"],"created_at":"2024-08-02T23:01:03.692Z","updated_at":"2025-05-06T20:31:41.505Z","avatar_url":"https://github.com/akshatdave.png","language":"Python","funding_links":[],"categories":["Polarization Imaging (DL)"],"sub_categories":[],"readme":"# PANDORA: Polarization-Aided Neural Decomposition Of Radiance\n### [Project Page](https://akshatdave.github.io/pandora) | [Paper](https://arxiv.org/abs/2203.13458) | [Data](https://drive.google.com/file/d/1FvOi_2wfSUnASHulQdBhHQcQCxOuJ8zz/view?usp=sharing)\n\u003cbr\u003e\nOfficial PyTorch implementation of Pandora: an inverse rendering technique that exploits neural implicit representations and polarization cues. \n\n\u003cbr\u003e\n\n[PANDORA: Polarization-Aided Neural Decomposition Of Radiance](https://akshatdave.github.io/pandora)\n\n [Akshat Dave](https://akshadave.github.io),\n [Yongyi Zhao](https://yongyizhao.com/),\n [Ashok Veeraraghavan](https://computationalimaging.rice.edu/team/ashok-veeraraghavan/) \n\n [Computational Imaging Lab, Rice University](https://computationalimaging.rice.edu)\n\naccepted for ECCV 2022\n\n![Teaser Animation](media/teaser_animation.gif)\n\n## Setting up\n### Loading conda environment\n\nCreate a new Anaconda environment using the supplied `environment.yml` \n```\nconda env create -f environment.yml\n```\n\n### Downloading datasets\n\nUnzip [this](https://drive.google.com/file/d/1FvOi_2wfSUnASHulQdBhHQcQCxOuJ8zz/view?usp=sharing) zip file (4.5 GB) into the `data` folder of the repo directory. The zip file contains real and rendered multi-view polarimetric datasets shown in the paper. \n\nRefer to `dataio/Ours.py` and `data/Mitsuba2.py` for pre-processing of real and rendered data respectively.\n\n## Training\n\nRun the following command to train geometry and radiance neural representations from multi-view polarimetric images.\n```\npython -m train --config configs/real_ceramic_owl.yaml\n```\nConfig files input through `--config` describe the parameters required for training. As an example the parameters for real ceramic owl dataset are described in `real_ceramic_owl.yaml`\n\nTensorboard logs, checkpoints, arguments and images are saved in the corresponding experiment folder in `logs/`.\n\n## Rendering Trained Representations\nUsing the saved arguments from `config.yaml` and the saved checkpoint such as `latest.pt` in `logs/`, novel views can be rendered using the following command.\n```\npython -m tools.render_view \n    --config  logs/our_ceramic_owl_v2/config.yaml\n    --load_pt logs/our_ceramic_owl_v2/ckpts/latest.pt\n```\nRefer to [this](https://github.com/ventusff/neurecon/blob/main/docs/usage.md#evaluation-free-viewport-rendering) documentation in  `neurecon` repo for possible camera trajectories. By default first three views used for training are rendered. \n\nOutputs are saved in the corresponding experiment folder in `out/`. By default,the outputs include surface normal, diffuse radiance, specular radiance and combined radiance for each view along with the estimated roughness.\n\n## Acknowledgements\n\nThis repository adapts code or draws inspiration from\n\n- https://github.com/ventusff/neurecon\n- https://github.com/yenchenlin/nerf-pytorch\n- https://github.com/Fyusion/LLFF\n- https://github.com/elerac/polanalyser\n- https://github.com/sxyu/svox2\n\n## Citation\n\n```\n@article{dave2022pandora,\n  title={PANDORA: Polarization-Aided Neural Decomposition Of Radiance},\n  author={Dave, Akshat and Zhao, Yongyi and Veeraraghavan, Ashok},\n  journal={arXiv preprint arXiv:2203.13458},\n  year={2022}\n}\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/akshatdave.github.io%2Fpandora%2F","html_url":"https://awesome.ecosyste.ms/projects/akshatdave.github.io%2Fpandora%2F","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/akshatdave.github.io%2Fpandora%2F/lists"}