[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-72522":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":25,"hasPages":23,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":37,"readmeContent":38,"aiSummary":39,"trendingCount":16,"starSnapshotCount":16,"syncStatus":18,"lastSyncTime":40,"discoverSource":41},72522,"MeshAnything","buaacyw\u002FMeshAnything","buaacyw","[ICLR 2025] From anything to mesh like human artists. Official impl. of \"MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers\"","https:\u002F\u002Fbuaacyw.github.io\u002Fmesh-anything\u002F",null,"Python",2286,105,31,22,0,1,2,8,3,61.88,"Other",false,"main",true,[27,28,29,30,31,32,33,34,35,36],"3d","auto-regressive-model","generative-ai","generative-model","iclr2025","large-language-models","mesh","mesh-generation","point-cloud","transformers","2026-06-12 04:01:06","\u003Cp align=\"center\">\n  \u003Ch3 align=\"center\">\u003Cstrong>MeshAnything:\u003Cbr> Artist-Created Mesh Generation\u003Cbr> with Autoregressive Transformers\u003C\u002Fstrong>\u003C\u002Fh3>\n\n\u003Cp align=\"center\">\n    \u003Ca href=\"https:\u002F\u002Fbuaacyw.github.io\u002F\">Yiwen Chen\u003C\u002Fa>\u003Csup>1,2*\u003C\u002Fsup>,\n    \u003Ca href=\"https:\u002F\u002Ftonghe90.github.io\u002F\">Tong He\u003C\u002Fa>\u003Csup>2†\u003C\u002Fsup>,\n    \u003Ca href=\"https:\u002F\u002Fdihuang.me\u002F\">Di Huang\u003C\u002Fa>\u003Csup>2\u003C\u002Fsup>,\n    \u003Ca href=\"https:\u002F\u002Fywcmaike.github.io\u002F\">Weicai Ye\u003C\u002Fa>\u003Csup>2\u003C\u002Fsup>,\n    \u003Ca href=\"https:\u002F\u002Fch3cook-fdu.github.io\u002F\">Sijin Chen\u003C\u002Fa>\u003Csup>3\u003C\u002Fsup>,\n    \u003Ca href=\"https:\u002F\u002Fme.kiui.moe\u002F\">Jiaxiang Tang\u003C\u002Fa>\u003Csup>4\u003C\u002Fsup>\u003Cbr>\n    \u003Ca href=\"https:\u002F\u002Fchenxin.tech\u002F\">Xin Chen\u003C\u002Fa>\u003Csup>5\u003C\u002Fsup>,\n    \u003Ca href=\"https:\u002F\u002Fcaizhongang.github.io\u002F\">Zhongang Cai\u003C\u002Fa>\u003Csup>6\u003C\u002Fsup>,\n    \u003Ca href=\"https:\u002F\u002Fscholar.google.com.hk\u002Fcitations?user=jZH2IPYAAAAJ&hl=en\">Lei Yang\u003C\u002Fa>\u003Csup>6\u003C\u002Fsup>,\n    \u003Ca href=\"https:\u002F\u002Fwww.skicyyu.org\u002F\">Gang Yu\u003C\u002Fa>\u003Csup>7\u003C\u002Fsup>,\n    \u003Ca href=\"https:\u002F\u002Fguosheng.github.io\u002F\">Guosheng Lin\u003C\u002Fa>\u003Csup>1†\u003C\u002Fsup>,\n    \u003Ca href=\"https:\u002F\u002Ficoz69.github.io\u002F\">Chi Zhang\u003C\u002Fa>\u003Csup>8†\u003C\u002Fsup>\n    \u003Cbr>\n    \u003Csup>*\u003C\u002Fsup>Work done during a research internship at Shanghai AI Lab.\n    \u003Cbr>\n    \u003Csup>†\u003C\u002Fsup>Corresponding authors.\n    \u003Cbr>\n    \u003Csup>1\u003C\u002Fsup>S-Lab, Nanyang Technological University,\n    \u003Csup>2\u003C\u002Fsup>Shanghai AI Lab,\n    \u003Cbr>\n    \u003Csup>3\u003C\u002Fsup>Fudan University,\n    \u003Csup>4\u003C\u002Fsup>Peking University,\n    \u003Csup>5\u003C\u002Fsup>University of Chinese Academy of Sciences,\n    \u003Cbr>\n    \u003Csup>6\u003C\u002Fsup>SenseTime Research,\n    \u003Csup>7\u003C\u002Fsup>Stepfun,\n    \u003Csup>8\u003C\u002Fsup>Westlake University\n\u003C\u002Fp>\n\n\n\u003Cdiv align=\"center\">\n\n\u003Ca href='https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.10163'>\u003Cimg src='https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FarXiv-2406.10163-b31b1b.svg'>\u003C\u002Fa>     \n \u003Ca href='https:\u002F\u002Fbuaacyw.github.io\u002Fmesh-anything\u002F'>\u003Cimg src='https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FProject-Page-Green'>\u003C\u002Fa>     \n \u003Ca href='https:\u002F\u002Fgithub.com\u002Fbuaacyw\u002FMeshAnything\u002Fblob\u002Fmaster\u002FLICENSE.txt'>\u003Cimg src='https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-SLab-blue'>\u003C\u002Fa>     \n\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002FYiwen-ntu\u002FMeshAnything\u002Ftree\u002Fmain\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F%F0%9F%A4%97%20Weights-HF-orange\">\u003C\u002Fa>     \n\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fspaces\u002FYiwen-ntu\u002FMeshAnything\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F%F0%9F%A4%97%20Gradio%20Demo-HF-orange\">\u003C\u002Fa>\n\n\u003C\u002Fdiv>\n\n\n\u003Cp align=\"center\">\n    \u003Cimg src=\"demo\u002Fdemo_video.gif\" alt=\"Demo GIF\" width=\"512px\" \u002F>\n\u003C\u002Fp>\n\n\n## Release\n- [6\u002F17] 🔥🔥 Try our newly released **[MeshAnything V2](https:\u002F\u002Fgithub.com\u002Fbuaacyw\u002FMeshAnythingV2)**. Maximum face number is increased to **1600** in V2 with better performance.\n- [6\u002F17] 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- [Training](#training)\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:\u002F\u002Fgithub.com\u002Fbuaacyw\u002FMeshAnything.git && 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:\u002F\u002Fdownload.pytorch.org\u002Fwhl\u002Fcu118\npip install -r requirements.txt\npip install flash-attn --no-build-isolation\n```\nor\n```shell\npip install git+https:\u002F\u002Fgithub.com\u002Fbuaacyw\u002FMeshAnything.git\n```\nAnd directly use in your code as\n```\nimport MeshAnything\n```\n\n## Usage\n### Local Gradio Demo \u003Ca href='https:\u002F\u002Fgithub.com\u002Fgradio-app\u002Fgradio'>\u003Cimg src='https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fgradio-app\u002Fgradio'>\u003C\u002Fa>\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\u002Fwand.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\u002Fmouse.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:\u002F\u002Fgithub.com\u002Fdeepseek-ai\u002FDreamCraft3D)) as the input of MeshAnything.\n- Please refer to https:\u002F\u002Fhuggingface.co\u002Fspaces\u002FYiwen-ntu\u002FMeshAnything\u002Ftree\u002Fmain\u002Fexamples for more examples.\n\n## Training\nPlease refer to the training code of MeshAnythingV2 at https:\u002F\u002Fgithub.com\u002Fbuaacyw\u002FMeshAnythingV2.\n\n## Acknowledgement\n\nOur code is based on these wonderful repos:\n\n* [MeshGPT](https:\u002F\u002Fnihalsid.github.io\u002Fmesh-gpt\u002F)\n* [meshgpt-pytorch](https:\u002F\u002Fgithub.com\u002Flucidrains\u002Fmeshgpt-pytorch)\n* [Michelangelo](https:\u002F\u002Fgithub.com\u002FNeuralCarver\u002FMichelangelo)\n* [transformers](https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Ftransformers)\n* [vector-quantize-pytorch](https:\u002F\u002Fgithub.com\u002Flucidrains\u002Fvector-quantize-pytorch)\n\n## Star History\n\n[![Star History Chart](https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=buaacyw\u002FMeshAnything&type=Date)](https:\u002F\u002Fstar-history.com\u002F#buaacyw\u002FMeshAnything&Date)\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","MeshAnything 是一个利用自回归变换器生成艺术家级3D网格模型的项目。其核心功能是基于给定的输入（如图像或点云），自动生成高质量的3D网格模型，这一过程模仿了人类艺术家的创作方式。该项目采用Python开发，依赖于先进的自回归模型和生成式AI技术，能够处理复杂的几何结构并保持细节的准确性。适合应用于需要高质量3D内容生成的场景，比如游戏开发、虚拟现实环境构建以及数字艺术创作等领域。","2026-06-11 03:42:24","high_star"]