{"id":15036544,"url":"https://github.com/buaacyw/meshanything","last_synced_at":"2025-05-15T09:08:45.356Z","repository":{"id":244682224,"uuid":"815946742","full_name":"buaacyw/MeshAnything","owner":"buaacyw","description":"[ICLR 2025] From anything to mesh like human artists. Official impl. of \"MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers\"","archived":false,"fork":false,"pushed_at":"2025-04-28T16:37:20.000Z","size":83635,"stargazers_count":2177,"open_issues_count":22,"forks_count":94,"subscribers_count":31,"default_branch":"main","last_synced_at":"2025-05-15T09:08:34.685Z","etag":null,"topics":["3d","auto-regressive-model","generative-ai","generative-model","iclr2025","large-language-models","mesh","mesh-generation","point-cloud","transformers"],"latest_commit_sha":null,"homepage":"https://buaacyw.github.io/mesh-anything/","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/buaacyw.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","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":"2024-06-16T16:02:59.000Z","updated_at":"2025-05-13T02:17:34.000Z","dependencies_parsed_at":"2024-08-05T19:48:23.031Z","dependency_job_id":"90569115-d255-4dc6-b1ac-66e825233bea","html_url":"https://github.com/buaacyw/MeshAnything","commit_stats":null,"previous_names":["buaacyw/meshanything"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/buaacyw%2FMeshAnything","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/buaacyw%2FMeshAnything/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/buaacyw%2FMeshAnything/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/buaacyw%2FMeshAnything/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/buaacyw","download_url":"https://codeload.github.com/buaacyw/MeshAnything/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254310520,"owners_count":22049470,"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","auto-regressive-model","generative-ai","generative-model","iclr2025","large-language-models","mesh","mesh-generation","point-cloud","transformers"],"created_at":"2024-09-24T20:31:29.607Z","updated_at":"2025-05-15T09:08:40.347Z","avatar_url":"https://github.com/buaacyw.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n  \u003ch3 align=\"center\"\u003e\u003cstrong\u003eMeshAnything:\u003cbr\u003e Artist-Created Mesh Generation\u003cbr\u003e with Autoregressive Transformers\u003c/strong\u003e\u003c/h3\u003e\n\n\u003cp align=\"center\"\u003e\n    \u003ca href=\"https://buaacyw.github.io/\"\u003eYiwen Chen\u003c/a\u003e\u003csup\u003e1,2*\u003c/sup\u003e,\n    \u003ca href=\"https://tonghe90.github.io/\"\u003eTong He\u003c/a\u003e\u003csup\u003e2†\u003c/sup\u003e,\n    \u003ca href=\"https://dihuang.me/\"\u003eDi Huang\u003c/a\u003e\u003csup\u003e2\u003c/sup\u003e,\n    \u003ca href=\"https://ywcmaike.github.io/\"\u003eWeicai Ye\u003c/a\u003e\u003csup\u003e2\u003c/sup\u003e,\n    \u003ca href=\"https://ch3cook-fdu.github.io/\"\u003eSijin Chen\u003c/a\u003e\u003csup\u003e3\u003c/sup\u003e,\n    \u003ca href=\"https://me.kiui.moe/\"\u003eJiaxiang Tang\u003c/a\u003e\u003csup\u003e4\u003c/sup\u003e\u003cbr\u003e\n    \u003ca href=\"https://chenxin.tech/\"\u003eXin Chen\u003c/a\u003e\u003csup\u003e5\u003c/sup\u003e,\n    \u003ca href=\"https://caizhongang.github.io/\"\u003eZhongang Cai\u003c/a\u003e\u003csup\u003e6\u003c/sup\u003e,\n    \u003ca href=\"https://scholar.google.com.hk/citations?user=jZH2IPYAAAAJ\u0026hl=en\"\u003eLei Yang\u003c/a\u003e\u003csup\u003e6\u003c/sup\u003e,\n    \u003ca href=\"https://www.skicyyu.org/\"\u003eGang Yu\u003c/a\u003e\u003csup\u003e7\u003c/sup\u003e,\n    \u003ca href=\"https://guosheng.github.io/\"\u003eGuosheng Lin\u003c/a\u003e\u003csup\u003e1†\u003c/sup\u003e,\n    \u003ca href=\"https://icoz69.github.io/\"\u003eChi Zhang\u003c/a\u003e\u003csup\u003e8†\u003c/sup\u003e\n    \u003cbr\u003e\n    \u003csup\u003e*\u003c/sup\u003eWork done during a research internship at Shanghai AI Lab.\n    \u003cbr\u003e\n    \u003csup\u003e†\u003c/sup\u003eCorresponding authors.\n    \u003cbr\u003e\n    \u003csup\u003e1\u003c/sup\u003eS-Lab, Nanyang Technological University,\n    \u003csup\u003e2\u003c/sup\u003eShanghai AI Lab,\n    \u003cbr\u003e\n    \u003csup\u003e3\u003c/sup\u003eFudan University,\n    \u003csup\u003e4\u003c/sup\u003ePeking University,\n    \u003csup\u003e5\u003c/sup\u003eUniversity of Chinese Academy of Sciences,\n    \u003cbr\u003e\n    \u003csup\u003e6\u003c/sup\u003eSenseTime Research,\n    \u003csup\u003e7\u003c/sup\u003eStepfun,\n    \u003csup\u003e8\u003c/sup\u003eWestlake University\n\u003c/p\u003e\n\n\n\u003cdiv align=\"center\"\u003e\n\n\u003ca href='https://arxiv.org/abs/2406.10163'\u003e\u003cimg src='https://img.shields.io/badge/arXiv-2406.10163-b31b1b.svg'\u003e\u003c/a\u003e \u0026nbsp;\u0026nbsp;\u0026nbsp;\u0026nbsp;\n \u003ca href='https://buaacyw.github.io/mesh-anything/'\u003e\u003cimg src='https://img.shields.io/badge/Project-Page-Green'\u003e\u003c/a\u003e \u0026nbsp;\u0026nbsp;\u0026nbsp;\u0026nbsp;\n \u003ca href='https://github.com/buaacyw/MeshAnything/blob/master/LICENSE.txt'\u003e\u003cimg src='https://img.shields.io/badge/License-SLab-blue'\u003e\u003c/a\u003e \u0026nbsp;\u0026nbsp;\u0026nbsp;\u0026nbsp;\n\u003ca href=\"https://huggingface.co/Yiwen-ntu/MeshAnything/tree/main\"\u003e\u003cimg src=\"https://img.shields.io/badge/%F0%9F%A4%97%20Weights-HF-orange\"\u003e\u003c/a\u003e \u0026nbsp;\u0026nbsp;\u0026nbsp;\u0026nbsp;\n\u003ca href=\"https://huggingface.co/spaces/Yiwen-ntu/MeshAnything\"\u003e\u003cimg src=\"https://img.shields.io/badge/%F0%9F%A4%97%20Gradio%20Demo-HF-orange\"\u003e\u003c/a\u003e\n\n\u003c/div\u003e\n\n\n\u003cp align=\"center\"\u003e\n    \u003cimg src=\"demo/demo_video.gif\" alt=\"Demo GIF\" width=\"512px\" /\u003e\n\u003c/p\u003e\n\n\n## Release\n- [6/17] 🔥🔥 Try our newly released **[MeshAnything V2](https://github.com/buaacyw/MeshAnythingV2)**. Maximum face number is increased to **1600** in V2 with better performance.\n- [6/17] We released the 350m version of **MeshAnything**.\n\n## Contents\n- [Release](#release)\n- [Contents](#contents)\n- [Installation](#installation)\n- [Usage](#usage)\n- [Important Notes](#important-notes)\n- [TODO](#todo)\n- [Acknowledgement](#acknowledgement)\n- [Star History](#star-history)\n- [BibTeX](#bibtex)\n\n## Installation\nOur environment has been tested on Ubuntu 22, CUDA 11.8 with A100, A800 and A6000.\n1. Clone our repo and create conda environment\n```\ngit clone https://github.com/buaacyw/MeshAnything.git \u0026\u0026 cd MeshAnything\nconda create -n MeshAnything python==3.10.13 -y\nconda activate MeshAnything\npip install torch==2.1.1 torchvision==0.16.1 torchaudio==2.1.1 --index-url https://download.pytorch.org/whl/cu118\npip install -r requirements.txt\npip install flash-attn --no-build-isolation\n```\nor\n```shell\npip install git+https://github.com/buaacyw/MeshAnything.git\n```\nAnd directly use in your code as\n```\nimport MeshAnything\n```\n\n## Usage\n### Local Gradio Demo \u003ca href='https://github.com/gradio-app/gradio'\u003e\u003cimg src='https://img.shields.io/github/stars/gradio-app/gradio'\u003e\u003c/a\u003e\n```\npython app.py\n```\n\n### Mesh Command line inference\n```\n# folder input\npython main.py --input_dir examples --out_dir mesh_output --input_type mesh\n\n# single file input\npython main.py --input_path examples/wand.obj --out_dir mesh_output --input_type mesh\n\n# Preprocess with Marching Cubes first\npython main.py --input_dir examples --out_dir mesh_output --input_type mesh --mc\n```\n### Point Cloud Command line inference\n```\n# Note: if you want to use your own point cloud, please make sure the normal is included.\n# The file format should be a .npy file with shape (N, 6), where N is the number of points. The first 3 columns are the coordinates, and the last 3 columns are the normal.\n\n# inference for folder\npython main.py --input_dir pc_examples --out_dir pc_output --input_type pc_normal\n\n# inference for single file\npython main.py --input_path pc_examples/mouse.npy --out_dir pc_output --input_type pc_normal\n```\n\n## Important Notes\n- It takes about 7GB and 30s to generate a mesh on an A6000 GPU.\n- The input mesh will be normalized to a unit bounding box. The up vector of the input mesh should be +Y for better results.\n- Limited by computational resources, MeshAnything is trained on meshes with fewer than 800 faces and cannot generate meshes with more than 800 faces. The shape of the input mesh should be sharp enough; otherwise, it will be challenging to represent it with only 800 faces. Thus, feed-forward 3D generation methods may often produce bad results due to insufficient shape quality. We suggest using results from 3D reconstruction, scanning and SDS-based method (like [DreamCraft3D](https://github.com/deepseek-ai/DreamCraft3D)) as the input of MeshAnything.\n- Please refer to https://huggingface.co/spaces/Yiwen-ntu/MeshAnything/tree/main/examples for more examples.\n## TODO\n\nThe repo is still being under construction, thanks for your patience. \n- [ ] Release of training code.\n- [ ] Release of larger model.\n\n## Acknowledgement\n\nOur code is based on these wonderful repos:\n\n* [MeshGPT](https://nihalsid.github.io/mesh-gpt/)\n* [meshgpt-pytorch](https://github.com/lucidrains/meshgpt-pytorch)\n* [Michelangelo](https://github.com/NeuralCarver/Michelangelo)\n* [transformers](https://github.com/huggingface/transformers)\n* [vector-quantize-pytorch](https://github.com/lucidrains/vector-quantize-pytorch)\n\n## Star History\n\n[![Star History Chart](https://api.star-history.com/svg?repos=buaacyw/MeshAnything\u0026type=Date)](https://star-history.com/#buaacyw/MeshAnything\u0026Date)\n\n## BibTeX\n```\n@misc{chen2024meshanything,\n  title={MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers},\n  author={Yiwen Chen and Tong He and Di Huang and Weicai Ye and Sijin Chen and Jiaxiang Tang and Xin Chen and Zhongang Cai and Lei Yang and Gang Yu and Guosheng Lin and Chi Zhang},\n  year={2024},\n  eprint={2406.10163},\n  archivePrefix={arXiv},\n  primaryClass={cs.CV}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbuaacyw%2Fmeshanything","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbuaacyw%2Fmeshanything","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbuaacyw%2Fmeshanything/lists"}