{"id":20405688,"url":"https://github.com/skyworkai/gamba","last_synced_at":"2025-09-04T20:33:11.133Z","repository":{"id":246382509,"uuid":"817757293","full_name":"SkyworkAI/Gamba","owner":"SkyworkAI","description":"Gamba: Marry Gaussian Splatting with Mamba for single view 3D reconstruction","archived":false,"fork":false,"pushed_at":"2024-06-28T03:05:11.000Z","size":1160,"stargazers_count":101,"open_issues_count":4,"forks_count":4,"subscribers_count":6,"default_branch":"main","last_synced_at":"2024-12-24T13:11:28.580Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://florinshen.github.io/gamba-project","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/SkyworkAI.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}},"created_at":"2024-06-20T11:30:18.000Z","updated_at":"2024-12-11T08:17:18.000Z","dependencies_parsed_at":null,"dependency_job_id":"9a497345-b425-4336-b213-5ebb0d949647","html_url":"https://github.com/SkyworkAI/Gamba","commit_stats":null,"previous_names":["skyworkai/gamba"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SkyworkAI%2FGamba","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SkyworkAI%2FGamba/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SkyworkAI%2FGamba/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SkyworkAI%2FGamba/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/SkyworkAI","download_url":"https://codeload.github.com/SkyworkAI/Gamba/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":231992776,"owners_count":18457252,"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":"2024-11-15T05:12:28.889Z","updated_at":"2024-12-31T14:13:43.366Z","avatar_url":"https://github.com/SkyworkAI.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n## Gamba\n\nThis is the official implementation of *Gamba: Marry Gaussian Splatting with Mamba for single view 3D reconstruction*.\n\n### [Project Page](https://florinshen.github.io/gamba-project) | [Arxiv](https://arxiv.org/abs/2403.18795) | [Weights](https://huggingface.co/florinshen/Gamba)\n\n### Why Gamba\n🔥 Reconstruct 3D object from a single image input within 50 milliseconds. \n\n\n🔥 First end-to-end trainable single-view reconstruction model with 3DGS.\n\nhttps://github.com/SkyworkAI/Gamba/assets/44775545/21bdc4e7-e070-446a-8fb7-401c9ee69921\n\n### Install\n\n```bash\n# xformers is required! please refer to https://github.com/facebookresearch/xformers for details.\n# for example, we use torch 2.1.0 + cuda 11.8\npip install torch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 --index-url https://download.pytorch.org/whl/cu118\npip install causal-conv1d==1.2.0 mamba-ssm\ngit clone --recursive git@github.com:SkyworkAI/Gamba.git\n# a modified gaussian splatting (+ depth, alpha rendering)\npip install ./submodules/diff-gaussian-rasterization\n# radial polygon mask, only in training,\npip install ./submodules/rad-polygon-mask\n\n# for mesh extraction\npip install git+https://github.com/NVlabs/nvdiffrast\n\n# other dependencies\npip install -r requirements.txt\n```\n\n### Pretrained Weights\n\nOur pretrained weight can be downloaded from [huggingface](https://huggingface.co/florinshen/Gamba). A lager Model is comming on the way!\n\nFor example, to download the bf16 model for inference:\n```bash\nmkdir checkpoint \u0026\u0026 cd checkpoint\nwget https://huggingface.co/florinshen/Gamba/resolve/main/gamba_ep399.pth\ncd ..\n```\n\n### Inference\n\nInference takes about 1.5GB GPU memory within 50 milliseconds.\n\n```bash\nbash scripts/test.sh\n```\n\nFor more options, please check [options](./core/options.py).\n\n### Training\n\nWe will update training tutorials soon. \n\n\n### Acknowledgement\n\nThis work is built on many amazing research works and open-source projects, thanks a lot to all the authors for sharing!\n\n- [LGM](https://github.com/3DTopia/LGM)\n- [OpenLRM](https://github.com/3DTopia/OpenLRM)\n- [gaussian-splatting](https://github.com/graphdeco-inria/gaussian-splatting) and [diff-gaussian-rasterization](https://github.com/graphdeco-inria/diff-gaussian-rasterization)\n- [nvdiffrast](https://github.com/NVlabs/nvdiffrast)\n- [dearpygui](https://github.com/hoffstadt/DearPyGui)\n- [tyro](https://github.com/brentyi/tyro)\n\n### Citation\n\n```bibtex\n@article{shen2024gamba,\n  title={Gamba: Marry gaussian splatting with mamba for single view 3d reconstruction},\n  author={Shen, Qiuhong and Wu, Zike and Yi, Xuanyu and Zhou, Pan and Zhang, Hanwang and Yan, Shuicheng and Wang, Xinchao},\n  journal={arXiv preprint arXiv:2403.18795},\n  year={2024}\n}\n```\nPlease also check our another project for unified 3D generation [MVGamba](https://arxiv.org/abs/2406.06367). The code and pretrained weights will also be released soon.\n\n```bibtex\n@article{yi2024mvgamba,\n  title={MVGamba: Unify 3D Content Generation as State Space Sequence Modeling},\n  author={Yi, Xuanyu and Wu, Zike and Shen, Qiuhong and Xu, Qingshan and Zhou, Pan and Lim, Joo-Hwee and Yan, Shuicheng and Wang, Xinchao and Zhang, Hanwang},\n  journal={arXiv preprint arXiv:2406.06367},\n  year={2024}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fskyworkai%2Fgamba","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fskyworkai%2Fgamba","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fskyworkai%2Fgamba/lists"}