{"id":29201837,"url":"https://github.com/pythonicforge/triposr-implementation","last_synced_at":"2025-07-02T12:07:31.607Z","repository":{"id":298640078,"uuid":"1000611028","full_name":"pythonicforge/TripoSR-Implementation","owner":"pythonicforge","description":"🧠 Reimplementation of TripoSR for 2D-to-3D object reconstruction using Colab and Hugging Face.","archived":false,"fork":false,"pushed_at":"2025-06-12T04:40:55.000Z","size":37,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-06-12T05:34:47.720Z","etag":null,"topics":["computer-vision","deep-learning","huggingface","lrm","paper-reproduction","python","triposr"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/pythonicforge.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-06-12T03:59:47.000Z","updated_at":"2025-06-12T04:42:44.000Z","dependencies_parsed_at":"2025-06-12T05:44:52.803Z","dependency_job_id":null,"html_url":"https://github.com/pythonicforge/TripoSR-Implementation","commit_stats":null,"previous_names":["pythonicforge/triposr-implementation"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/pythonicforge/TripoSR-Implementation","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pythonicforge%2FTripoSR-Implementation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pythonicforge%2FTripoSR-Implementation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pythonicforge%2FTripoSR-Implementation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pythonicforge%2FTripoSR-Implementation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pythonicforge","download_url":"https://codeload.github.com/pythonicforge/TripoSR-Implementation/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pythonicforge%2FTripoSR-Implementation/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":263137419,"owners_count":23419298,"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":["computer-vision","deep-learning","huggingface","lrm","paper-reproduction","python","triposr"],"created_at":"2025-07-02T12:07:26.785Z","updated_at":"2025-07-02T12:07:31.597Z","avatar_url":"https://github.com/pythonicforge.png","language":"Jupyter Notebook","readme":"# TripoSR Reimplementation\r\n\r\nThis is a clean and reproducible **Colab-based reimplementation** of [Stability AI's TripoSR](https://huggingface.co/stabilityai/TripoSR) — a powerful zero-shot model that generates 3D object meshes from a single 2D image.\r\n\r\nBuilt on top of the [PyImageSearch blog tutorial]([https://pyimagesearch.com/](https://pyimagesearch.com/2024/11/25/create-a-3d-object-from-your-images-with-triposr-in-python/)), this notebook integrates:\r\n\r\n- 2D input image upload\r\n- Background removal via `rembg`\r\n- Inference using TripoSR via `Hugging Face`\r\n- 360° turntable render output\r\n- Mesh export in `.obj` format\r\n\r\n\u003cbr/\u003e\r\n\r\n## Project Highlights\r\n\r\n- **Zero-shot inference**: No need for fine-tuning — just drop an image and get a 3D model\r\n- **Background cleanup**: Uses `rembg` for cleaner foreground object extraction\r\n- **Smooth renders**: Generates 30-angle renders + MP4 video\r\n- **Mesh export**: Outputs ready-to-use 3D `.obj` files\r\n\r\n\u003cbr/\u003e\r\n\r\n## How to Use (in Colab)\r\n\r\n1. **Open the Colab notebook**  \r\n   \u003e [▶️ Click here to run in Colab](https://colab.research.google.com/drive/127g5BFZoHsj4dt6nspENpLUN6RRX9Ldr?usp=sharing)\r\n\r\n2. **Upload an image** (preferably product-style or with clear foreground)\r\n\r\n3. **Run all cells**  \r\n   Sit back and let the notebook:\r\n   - Process the image\r\n   - Run the TripoSR model\r\n   - Render 360° views\r\n   - Export a `.obj` 3D mesh\r\n\r\n4. **Preview your result!**  \r\n   A video preview will auto-play inside the notebook 🎬\r\n\r\n\u003cbr/\u003e\r\n\r\n## Output Structure\r\n\r\nAfter running the notebook, your `output/` folder will look like this:\r\n\r\noutput/\r\n\u003cbr/\u003e\r\n└── 0/\r\n\u003cbr/\u003e\r\n├── input.png # Processed input image\r\n\u003cbr/\u003e\r\n├── render_000.png # 30 rendered views\r\n\u003cbr/\u003e\r\n├── render_001.png\r\n\u003cbr/\u003e\r\n├── ...\r\n\u003cbr/\u003e\r\n├── render.mp4 # Turntable video\r\n\u003cbr/\u003e\r\n└── mesh.obj # Exported mesh\r\n\r\n\u003cbr/\u003e\r\n\r\n## References\r\n\r\n- [TripoSR on Hugging Face](https://huggingface.co/stabilityai/TripoSR)\r\n- [Original PyImageSearch tutorial](https://pyimagesearch.com/2024/11/25/create-a-3d-object-from-your-images-with-triposr-in-python/)\r\n- [Paper: TripoSR: Ultra-Fast 3D Reconstruction from a Single Image](https://arxiv.org/pdf/2403.02151)\r\n\r\n\u003cbr/\u003e\r\n\r\n## Future Plans\r\n\r\n- [ ] Wrap this into an end-to-end web app\r\n- [ ] Dockerize for easier deployment\r\n- [ ] Add sample gallery + download links\r\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpythonicforge%2Ftriposr-implementation","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpythonicforge%2Ftriposr-implementation","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpythonicforge%2Ftriposr-implementation/lists"}