寓言 5.1 世界建模
Fable 5.1 World Modeling

原始链接: https://github.com/PhiloLabs/fable51-worlds

本项目引入了一套浏览器原生系统,利用自主人工智能智能体集群,生成可探索的现实世界 3D 重建场景。该系统不依赖传统游戏引擎或私有图块,而是使用开源代码和公共数据(OSM、USGS),构建出高精度的 Three.js 环境。 首个构建版本展示了旧金山的联合广场,包含 453 个建筑基底、129 个已识别店面、运行中的交通流,以及苹果和任天堂商店等详细的室内场景。其开发流程完全透明且可复现: 1. **侦察**:AI 智能体聚合站点数据与源图像。 2. **资产生成**:Blender 脚本自动创建优化的 GLB 资产。 3. **运行时**:轻量级 Three.js 应用程序负责组装场景。 4. **验证**:严格的质量保证循环使用 Playwright 进行虚拟环境与现实照片的摄像机匹配,并由多学科 AI 智能体提供反馈,进行迭代优化。 从数据获取到渲染,该过程的每个阶段都已包含在代码库中。本项目采用开源协议(MIT),为在浏览器中重现物理世界提供了一个可扩展的、代码驱动的框架。

Hacker News 最新 | 过往 | 评论 | 提问 | 展示 | 招聘 | 提交 登录 Fable 5.1 世界建模 (github.com/philolabs) 16 分,由 surreal_ 在 46 分钟前发布 | 隐藏 | 过往 | 收藏 | 讨论 帮助 指南 | 常见问题 | 列表 | API | 安全 | 法律 | 申请 YC | 联系 搜索:
相关文章

原文

Worlds via code. Explorable, browser-native reconstructions of real places — researched, modelled, and quality-checked end to end by autonomous Claude Fable 5.1 agent swarms, then shipped as plain Three.js apps you can run with npm run dev.

No game engine. No proprietary 3D tiles. Every building, storefront, sign, tree and traffic light is generated from open data and public reference imagery by code that lives in this repo.


Union Square walkthrough: aerial sweep, Dewey Monument, Nintendo SAN FRANCISCO, Apple Union Square

Watch the full 59-second walkthrough · 1920×1080 · aerial, plaza, Nintendo, lower level, Apple

The square and its surrounding blocks — Powell, Geary, Post and Stockton — on real terrain and a real street grid, with 129 identified storefronts, working traffic lights and cable cars, day/sunset/night, and two explorable interiors: Apple Union Square (300 Post St) and Nintendo SAN FRANCISCO (331 Powell St).

Run it cd union-square-sf && npm install && npm run dev
Buildings 453 OSM footprints · 75 hand-authored façades · 129 named storefronts
Life 220 pedestrians on a 1,398-node nav graph · 109 vehicles incl. Powell St cable cars
Interiors Apple + Nintendo, 23 interactive objects
Validation 34 camera-matched viewpoints vs. real photographs · 147 comparison sheets · 9 independent reviewer reports

More worlds coming.


Each world follows the same pipeline, and every stage is in the repo so you can re-run it:

  1. Reconnaissance — parallel research agents pull OpenStreetMap geometry, USGS elevation, transit and street specs, and a storefront census with per-fact sources and confidence levels.
  2. Offline asset generation — Blender-as-a-library (bpy) scripts emit optimised GLB kits: façade modules, street furniture, vehicles, vegetation, retail fixtures, pedestrian body parts.
  3. Runtime — a pure Three.js app assembles terrain, streets, façades, props, crowds and traffic from JSON specs.
  4. Camera-match QA — Playwright drives the real app, screenshots fixed viewpoints, and diffs them against free-licensed photographs taken from the same spot; independent reviewer agents (architect, geographer, technical artist, interaction) file reports that drive the next fix cycle.

Code and generated assets: MIT. Geometry is derived from OpenStreetMap (ODbL) and USGS 3DEP (public domain). Reference photographs are not redistributed here — their provenance is recorded per sector in each world's refs/*/SOURCES.md. Brand names and logos identify the real businesses at their real locations and belong to their owners.

联系我们 contact @ memedata.com