[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-71085":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":9,"language":10,"languages":9,"totalLinesOfCode":9,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":15,"stars7d":16,"stars30d":16,"stars90d":15,"forks30d":15,"starsTrendScore":15,"compositeScore":17,"rankGlobal":9,"rankLanguage":9,"license":18,"archived":19,"fork":19,"defaultBranch":20,"hasWiki":21,"hasPages":19,"topics":22,"createdAt":9,"pushedAt":9,"updatedAt":23,"readmeContent":24,"aiSummary":25,"trendingCount":15,"starSnapshotCount":15,"syncStatus":26,"lastSyncTime":27,"discoverSource":28},71085,"point-e","openai\u002Fpoint-e","openai","Point cloud diffusion for 3D model synthesis",null,"Python",6885,798,212,64,0,1,39.71,"MIT License",false,"main",true,[],"2026-06-12 02:02:47","# Point·E\n\n![Animation of four 3D point clouds rotating](point_e\u002Fexamples\u002Fpaper_banner.gif)\n\nThis is the official code and model release for [Point-E: A System for Generating 3D Point Clouds from Complex Prompts](https:\u002F\u002Farxiv.org\u002Fabs\u002F2212.08751).\n\n# Usage\n\nInstall with `pip install -e .`.\n\nTo get started with examples, see the following notebooks:\n\n * [image2pointcloud.ipynb](point_e\u002Fexamples\u002Fimage2pointcloud.ipynb) - sample a point cloud, conditioned on some example synthetic view images.\n * [text2pointcloud.ipynb](point_e\u002Fexamples\u002Ftext2pointcloud.ipynb) - use our small, worse quality pure text-to-3D model to produce 3D point clouds directly from text descriptions. This model's capabilities are limited, but it does understand some simple categories and colors.\n * [pointcloud2mesh.ipynb](point_e\u002Fexamples\u002Fpointcloud2mesh.ipynb) - try our SDF regression model for producing meshes from point clouds.\n\nFor our P-FID and P-IS evaluation scripts, see:\n\n * [evaluate_pfid.py](point_e\u002Fevals\u002Fscripts\u002Fevaluate_pfid.py)\n * [evaluate_pis.py](point_e\u002Fevals\u002Fscripts\u002Fevaluate_pis.py)\n\nFor our Blender rendering code, see [blender_script.py](point_e\u002Fevals\u002Fscripts\u002Fblender_script.py)\n\n# Samples\n\nYou can download the seed images and point clouds corresponding to the paper banner images [here](https:\u002F\u002Fopenaipublic.azureedge.net\u002Fmain\u002Fpoint-e\u002Fbanner_pcs.zip).\n\nYou can download the seed images used for COCO CLIP R-Precision evaluations [here](https:\u002F\u002Fopenaipublic.azureedge.net\u002Fmain\u002Fpoint-e\u002Fcoco_images.zip).\n","Point·E 是一个用于从复杂提示生成3D点云的系统。该项目通过扩散模型实现从图像或文本描述中生成3D点云，并支持将生成的点云转换为网格模型。其核心功能包括基于图像和文本输入生成3D点云，以及使用SDF回归模型将点云转化为网格。此外，项目还提供了P-FID和P-IS评估脚本及Blender渲染代码，以帮助用户评估和可视化生成结果。适用于需要快速原型设计、3D内容生成或计算机视觉研究等场景。",2,"2026-06-11 03:35:49","high_star"]