正在加载视频...

视频加载失败

Step into the map with the Street View grounding feature in Project Genie from Google DeepMind and Google Labs. Announced at I/O, this research prototype uses locations from Google Maps Street View as a foundation, letting you generate and explore interactive, 360-degree virtual environments from just a text prompt...

4,043,635 次观看 • 2 个月前 •via X (Twitter)

31 条评论

Google Labs 的头像
Google Labs2 个月前

@GoogleDeepMind @googlemaps 🌍✨🤩

Vanar 的头像
Vanar2 个月前

@GoogleDeepMind @GoogleLabs @googlemaps This is a glimpse of where AI is heading. From generating images to generating interactive worlds. Excited to see Google continue pushing the frontier.

🕷 Egon Inspirations_𝕏 的头像
🕷 Egon Inspirations_𝕏2 个月前

@GoogleDeepMind @GoogleLabs @googlemaps 😺❤️‍🔥👍

darkoss1 的头像
darkoss12 个月前

@GoogleDeepMind @GoogleLabs @googlemaps Another US-Only feature

RAZA | AI EXPLORER 的头像
RAZA | AI EXPLORER2 个月前

@GoogleDeepMind @GoogleLabs @googlemaps Amazing innovation from the team.

YYS 的头像
YYS2 个月前

@GoogleDeepMind @GoogleLabs @googlemaps

Inflectiv AI ⧉ 的头像
Inflectiv AI ⧉2 个月前

@GoogleDeepMind @GoogleLabs @googlemaps Grounding a world model in actual Street View imagery is a brilliant way to solve the lack of spatial coherence in generative media. It gives the AI a concrete geometric anchor so the environment layout stays consistent as you move through it.

Relax_to_Rich 的头像
Relax_to_Rich2 个月前

@GoogleDeepMind @GoogleLabs @googlemaps Real geographic data drastically boosts virtual scene realism and unlocks new commercial opportunities for tourism and game simulation industries.

Liam Turner 的头像
Liam Turner2 个月前

@GoogleDeepMind @GoogleLabs @googlemaps Great Share

sophia 𖥧 的头像
sophia 𖥧2 个月前

@GoogleDeepmind @GoogleLabs @GoogleMaps this is genuinely the most interesting thing google has shown in years

Samia | AI & Productivity 的头像
Samia | AI & Productivity2 个月前

@GoogleDeepMind @GoogleLabs @googlemaps Many people think AI replaces work. In reality, it removes repetitive tasks so you can focus on higher-value work

0xJedi | Legion 的头像
0xJedi | Legion2 个月前

@GoogleDeepMind @GoogleLabs @googlemaps The future is here

Jense Wart 的头像
Jense Wart2 个月前

@GoogleDeepMind @GoogleLabs @googlemaps Spot on! Completely agree with this. 👏

sophia b 的头像
sophia b2 个月前

@GoogleDeepmind @GoogleLabs @GoogleMaps finally a use for all those random street view angles i've saved over the years

✿ sophie ✿ 的头像
✿ sophie ✿2 个月前

@GoogleDeepmind @GoogleLabs @GoogleMaps does it work with any random street view location or only ones with good coverage

Christie 的头像
Christie2 个月前

okay this one is genuinely fun to think about. 🧠 you type a real address and google generates a fully explorable 360 degree world from it. the practical uses are interesting. virtual property tours, travel planning, accessibility for people who can't visit places physically. but the question nobody is asking yet is how do you verify what's real vs what the model filled in?

Victoria 的头像
Victoria2 个月前

@GoogleDeepMind @GoogleLabs @googlemaps Using Street View data to generate interactive 360 degree virtual environments from a text prompt is a practical application of generative AI that goes beyond chatbots. The frame by frame prediction makes it feel dynamic

sofi w 的头像
sofi w2 个月前

@GoogleDeepMind @GoogleLabs @googlemaps so can you walk around in it or is it just a static view

sophie c. 的头像
sophie c.2 个月前

@GoogleDeepmind @GoogleLabs @GoogleMaps so i can now virtually get lost in a neighborhood i've never been to, in full 360. love that for me

AI Mastery Guide 的头像
AI Mastery Guide2 个月前

@GoogleDeepMind @GoogleLabs @googlemaps Turning a real street view spot into a full explorable world is genuinely wild tech 🌍

HALUK GÜRŞEN 的头像
HALUK GÜRŞEN2 个月前

@GoogleDeepMind @GoogleLabs @googlemaps *****LEGEND

Henry Nguyen 的头像
Henry Nguyen2 个月前

@GoogleDeepMind @GoogleLabs @googlemaps this is fascinating — bridging grounded geospatial data with generative worlds feels like the first real step toward useful spatial AI, not just pretty demos.

sof 𖥧 的头像
sof 𖥧2 个月前

@GoogleDeepmind @GoogleLabs @GoogleMaps tried a similar grounding tool last month. trees kept spawning inside buildings. this looks way more stable

Emily 的头像
Emily2 个月前

@GoogleDeepMind @GoogleLabs @googlemaps imagining those street views together makes my heart feel all fluttery 💕

Ian Stinson 的头像
Ian Stinson2 个月前

@GoogleDeepMind @GoogleLabs @googlemaps Really useful framing. AI can speed up the work, but the product judgment still has to come from somewhere.

𖥧 sof 𖥧 的头像
𖥧 sof 𖥧2 个月前

@GoogleDeepmind @GoogleLabs @GoogleMaps wait so this can generate any street view location in 360?

Sophie 🧡 💛 💗 的头像
Sophie 🧡 💛 💗2 个月前

@GoogleDeepmind @GoogleLabs @GoogleMaps photogrammetry or neural radiance fields?

Alyssa 🍄 的头像
Alyssa 🍄2 个月前

@GoogleDeepmind @GoogleLabs @GoogleMaps not sure what I watched but okay

sophs s. 的头像
sophs s.2 个月前

@GoogleDeepMind @GoogleLabs @googlemaps this is just google street view with extra steps and i'm supposed to be impressed

SufianTech 的头像
SufianTech2 个月前

@GoogleDeepMind @GoogleLabs @googlemaps Impressive work! I can’t wait to see how developers use this for education, gaming, and virtual experiences. 🚀

Gregor 的头像
Gregor2 个月前

@GoogleDeepMind @GoogleLabs @googlemaps street view 'grounding' sounds more stable than it is. coverage thins fast outside major cities so most of what you're exploring is generated, not captured

相关视频

Without World Models, There Is No AGI. Google Just Proved It. If AGI ever happens, it will not come from bigger chatbots alone. From the very start of this interview, one thing is crystal clear: without world models, we will never reach AGI. And right now, Google is leading with its world simulator Genie 3. Here is the core of what Demis Hassabis explains in this conversation: • World models are the missing core of AGI Hassabis says his deepest long term focus has always been world models and simulations. Not just language. Not just prediction. Actual internal simulations of reality. • LLMs are impressive, but incomplete Language models understand more about the world than expected because human language encodes a lot of reality. Still, language is only a shadow of the real thing. • What text can never fully teach Reality includes things text struggles to express: •3D space and spatial dynamics •Physical causality and mechanics •Sensorimotor experience like movement, force, smell, or balance • Experience beats description To close the gap, AI must learn from interaction and experience, not just static text. That is how you build an internal world simulator. • Why Genie 3 matters With Google DeepMind pushing systems like Genie 3, AI starts to model reality itself, not just talk about it. • Robots and real world assistants depend on this True robotics, smart glasses, and universal assistants require AI that understands the physical world you live in, not just your screen. Bottom line: AGI will not emerge from better text prediction. It will emerge from systems that can simulate, predict, and understand reality itself. Right now, Google is clearly ahead on that path. Curious what you think. Are world models the real AGI unlock, or just another stepping stone?

VraserX e/acc

23,784 次观看 • 9 个月前