[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-1179":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":15,"stars7d":17,"stars30d":18,"stars90d":16,"forks30d":16,"starsTrendScore":19,"compositeScore":20,"rankGlobal":10,"rankLanguage":10,"license":10,"archived":21,"fork":21,"defaultBranch":22,"hasWiki":21,"hasPages":21,"topics":23,"createdAt":10,"pushedAt":10,"updatedAt":24,"readmeContent":25,"aiSummary":26,"trendingCount":16,"starSnapshotCount":16,"syncStatus":27,"lastSyncTime":28,"discoverSource":29},1179,"AnyRecon","OpenImagingLab\u002FAnyRecon","OpenImagingLab","AnyRecon: Arbitrary-View 3D Reconstruction with Video Diffusion Model","",null,"Python",354,18,11,5,0,7,26,15,56.94,false,"main",[],"2026-06-12 04:00:08","\u003Cp align=\"center\" >\n    \u003Cimg src=\"docs\u002Flogo.png\"  width=\"60%\" >\n\u003C\u002Fp>\n\n\u003Ch2 align=\"center\">AnyRecon: Arbitrary-View 3D Reconstruction\u003Cbr>with Video Diffusion Model\u003C\u002Fh2>\n\n\u003Cdiv align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fyutian10.github.io\">Yutian Chen\u003C\u002Fa>, \n  \u003Ca href=\"https:\u002F\u002Fguoshi28.github.io\">Shi Guo\u003C\u002Fa>, \n  \u003Ca href=\"https:\u002F\u002Frbjin.github.io\u002F\">Renbiao Jin\u003C\u002Fa>,\n  \u003Ca href=\"https:\u002F\u002Fscholar.google.com\u002Fcitations?user=9b5dE40AAAAJ&hl=en\">Tianshuo Yang\u003C\u002Fa>,\n  \u003Ca href=\"https:\u002F\u002Fcaixin98.github.io\u002F\">Xin Cai\u003C\u002Fa>, \n  \u003Ca href=\"https:\u002F\u002Fluo0207.github.io\u002Fyawenluo\u002F\">Yawen Luo\u003C\u002Fa>, \n  \u003Ca href=\"\">Mingxin Yang\u003C\u002Fa>, \u003Cbr>\n  \u003Ca href=\"https:\u002F\u002Fmulinyu.github.io\u002F\">Mulin Yu\u003C\u002Fa>, \n  \u003Ca href=\"https:\u002F\u002Feveneveno.github.io\u002Flnxu\u002F\">Linning Xu\u003C\u002Fa>, \n  \u003Ca href=\"https:\u002F\u002Ftianfan.info\u002F\">Tianfan Xue\u003C\u002Fa>\n\u003C\u002Fdiv>\n\n\u003Cbr>\n\n\u003Cp align=\"center\"> \u003Ca href='https:\u002F\u002Fyutian10.github.io\u002FAnyRecon\u002F'>\u003Cimg src='https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FProject-Page-Green'>\u003C\u002Fa>  \n\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fpdf\u002F2604.19747\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fstatic\u002Fv1?label=Arxiv&message=AnyRecon&color=red&logo=arxiv\">\u003C\u002Fa>  \n \u003Ca href='https:\u002F\u002Fhuggingface.co\u002FYutian10\u002FAnyRecon'>\u003Cimg src='https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F%F0%9F%A4%97%20Hugging%20Face-Model-yellow'>\u003C\u002Fa>  \n \u003Ca href='https:\u002F\u002Fyoutu.be\u002FsfgFZKCdofs'>\u003Cimg src='https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FYouTube-Video-FF0000?logo=youtube&logoColor=white'>\u003C\u002Fa>  \n\u003C\u002Fp>\n\n\u003Cp align=\"center\" width=\"100%\">\n    \u003Cimg src=\"docs\u002Fgif.gif\"  width=\"90%\" >\n\u003C\u002Fp>\n\n## TODO List\n\n- [ ] Upload sparse attention weight.\n\n## 🛠️ Environment Setup\n\n###  1. Clone Repository and Setup Environment\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002FOpenImagingLab\u002FAnyRecon.git\ncd AnyRecon\nconda create -n anyrecon python=3.10 -y\nconda activate anyrecon\npip install torch==2.4.1 torchvision==0.19.1 torchaudio==2.4.1 --index-url https:\u002F\u002Fdownload.pytorch.org\u002Fwhl\u002Fcu118\npip install -r requirements.txt\n```\n\n###  2. Download Models\nAnyRecon relies on specific pre-trained weights. Please download them and place them in the `.\u002Fcheckpoints` folder.\n\n- Base Video Diffusion Model (Wan2.1 I2V 14B 720P) [[download](https:\u002F\u002Fhuggingface.co\u002FWan-AI\u002FWan2.1-I2V-14B-720P\u002Ftree\u002Fmain)]\n- AnyRecon LoRA weights [[download](https:\u002F\u002Fhuggingface.co\u002FYutian10\u002FAnyRecon\u002Ftree\u002Fmain)]\n\n## 🚀 Quick Start\n\n### Inference\nYou can run the inference using the provided `test.sh` script:\n\n```bash\nbash test.sh\n```\n\nOr you can run the python script directly:\n```bash\npython run_AnyRecon.py \\\n    --root_dir example\u002Fvalley \\\n    --output_dir example\u002Fvalley \\\n    --lora_path full_attention.ckpt\n```\n\n## 💗 Acknowledgments\nThanks to these great repositories: [Wan2.1](https:\u002F\u002Fgithub.com\u002FWan-Video\u002FWan2.1) and [DiffSynth-Studio](https:\u002F\u002Fgithub.com\u002Fmodelscope\u002FDiffSynth-Studio).\n\n## 🔗 Citation\nIf you find our work helpful, please cite it:\n```\n@article{chen2026anyrecon,\n  title={AnyRecon: Arbitrary-View 3D Reconstruction with Video Diffusion Model},\n  author={Chen, Yutian and Guo, Shi and Jin, Renbiao and Yang, Tianshuo and Cai, Xin and Luo, Yawen and Yang, Mingxin and Yu, Mulin and Xu, Linning and Xue, Tianfan},\n  journal={arXiv preprint arXiv:2604.19747},\n  year={2026}\n}\n```\n","AnyRecon 是一个基于视频扩散模型的任意视角3D重建项目。其核心功能是通过输入视频，生成高质量、多角度的3D模型，利用了先进的视频扩散模型和LoRA权重技术来提升重建效果。该项目采用Python语言编写，并依赖于特定的预训练模型以实现高效准确的3D重建过程。AnyRecon 适用于需要从视频中提取并构建精细3D场景的应用场合，如虚拟现实内容创作、游戏开发以及影视特效制作等。",2,"2026-06-11 02:42:08","CREATED_QUERY"]