{"id":13563143,"url":"https://github.com/ReshotAI/gaussian-painters","last_synced_at":"2025-04-03T19:32:26.180Z","repository":{"id":192266542,"uuid":"686389515","full_name":"ReshotAI/gaussian-painters","owner":"ReshotAI","description":"Gaussian Painters using 3D Gaussian Splatting","archived":false,"fork":false,"pushed_at":"2024-08-26T21:16:44.000Z","size":2970,"stargazers_count":384,"open_issues_count":0,"forks_count":20,"subscribers_count":10,"default_branch":"main","last_synced_at":"2025-03-28T11:43:20.981Z","etag":null,"topics":["3d","ai","art","gaussian-splatting","machine-learning","nerf","painting","python","pytorch"],"latest_commit_sha":null,"homepage":"https://www.lingosub.com","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/ReshotAI.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","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":"2023-09-02T16:19:15.000Z","updated_at":"2025-02-14T21:57:49.000Z","dependencies_parsed_at":"2024-04-27T14:02:58.868Z","dependency_job_id":"221632aa-fbfa-4f97-a372-5c5b766c59ec","html_url":"https://github.com/ReshotAI/gaussian-painters","commit_stats":null,"previous_names":["reshotai/gaussian-painters"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ReshotAI%2Fgaussian-painters","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ReshotAI%2Fgaussian-painters/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ReshotAI%2Fgaussian-painters/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ReshotAI%2Fgaussian-painters/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ReshotAI","download_url":"https://codeload.github.com/ReshotAI/gaussian-painters/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247065407,"owners_count":20877769,"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","ai","art","gaussian-splatting","machine-learning","nerf","painting","python","pytorch"],"created_at":"2024-08-01T13:01:15.602Z","updated_at":"2025-04-03T19:32:25.740Z","avatar_url":"https://github.com/ReshotAI.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# Gaussian Painters\n\n**Sponsored by \u003cimg src=\"https://www.lingosub.com/icon.svg\" height=20 width=20 style=\"vertical-align: middle;\"/\u003e [LingoSub](https://www.lingosub.com): Learn languages by watching videos with AI-powered translations.**\n\n**and \u003cimg src=\"https://www.thumbnailspro.com/icon.svg\" height=20 width=20 style=\"vertical-align: middle;\"/\u003e [ThumbnailsPro](https://www.thumbnailspro.com): Instant AI-generated Thumbnails, for videos that get clicks.**\n\n\u003cblockquote\u003eThis is a fork of \u003ca href=\"https://github.com/graphdeco-inria/gaussian-splatting\"\u003e3D Gaussian Splatting\u003c/a\u003e. Refer to the original repo for instructions on how to run the code.\u003c/blockquote\u003e\n\n![](assets/gaussian_painter.jpg)\n\n## How to create a Gaussian Painter dataset\n\nAfter having installed the 3D Gaussian Splatting code, run the following command:\n\n```bash\npython create_dataset.py --img_path /path/to/image --output_dir /path/to/output_dir\n```\n\nYou can disable the `opacity_reset_interval` argument by setting it to 30_000.\n\nYou can also set `sh_degree` to 0 to disable viewdependent effects.\n\nThis will create a dataset ready to be trained with the Gaussian Splatting code.\n\n## Experiments\n\n- Orthogonal images (using `create_dataset2.py`)\n\nhttps://github.com/ReshotAI/gaussian-painters/assets/16474636/4799f0b6-ed29-412e-9875-4a790ecbbaaf\n\n- Steganography (using `create_dataset3.py`)\n\nhttps://github.com/ReshotAI/gaussian-painters/assets/16474636/9a391361-7d5b-40cc-ab67-97e15e53a913\n\n- Lenticular effect (using `create_dataset5.py`)\n\nThis code requires to install [kornia](https://github.com/kornia/kornia) using `pip install kornia`\n\nhttps://github.com/ReshotAI/gaussian-painters/assets/16474636/356ad0f6-3bcb-46fe-a6f8-421138e54222\n\n\n\n## Visualize the \"painting\" process\n\nUsing the SIBR visualizer, you can visualize the \"painting\" process during the Gaussian Splatting optimization.\n\n\nhttps://github.com/ReshotAI/gaussian-painters/assets/16474636/b29731b6-5fcc-43f5-a169-bfed2b109ce0\n\n\n\n## How it works?\n\nThe `create_dataset` script simply creates a COLMAP output directory with a single camera pointing at a plane. 100 points are sampled from the image and used as initial point cloud for the Gaussian Splatting optimization. A second perpendicular image is also created with a black image as target.\n\n![](assets/colmap.jpg)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FReshotAI%2Fgaussian-painters","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FReshotAI%2Fgaussian-painters","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FReshotAI%2Fgaussian-painters/lists"}