Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Got 2nd place in the Google DeepMind SG hackathon! I built a webapp that converts 2d topo maps into 3d colourful renders + lets you fly through and ask gemini live api what you're looking at.

ruban

1,366 subscribers

272,463 views • 9 months ago •via X (Twitter)

Arts Education Science & Technology

Anya Rossi• Live Now

Private livecam show

43 Comments

ruban9 months ago

1. download any @USGS topo map (.tif or .jpg) 2. pull elevation from @awscloud terrain tiles 3. @NanoBanana pro (via @fal) to colour the maps 4. hop on the plane with @GeminiApp live api as your tour guide

ruban9 months ago

here's a live demo: and the github repo:

ruban9 months ago

big shoutout to @agrimsingh for letting me in and thanks to @SherryYanJiang and the rest of the @65labslah team for organising the event :) happy to wear a gemini cap to the claude code meet up next week if you can get me one @thorwebdev

Sherry Jiang9 months ago

@GoogleDeepMind such a cool visually stunning project! the renders are insane.

ruban9 months ago

thanks sherry! you guys did such a great job organising :)

MAV 𖤓9 months ago

Hey, Ruban, how are you doing? We just created a token for your project! We’d absolutely love to onboard you into our ecosystem — you’re already receiving fees from it, so you're earning passively just by being part of this. Your friend @SherryYanJiang did the exact same thing with PeekMoney and it’s been working great for her! There will be a big hackathon too that you can be a part of it. @BagsHackathon You can learn more or dm @finnbags to understand! There's already 555$ for you to claim in minutes and will become much more with your endorsement and recognition. Feel free to DM me if you'd like to understand more!

ludwig9 months ago

@GoogleDeepMind very cool, also made me think of how crazy I’d have been abt this if this had been a thing years ago when I started…. I’d have spent so much more time building random stuff

Philipp Schmid9 months ago

@GoogleDeepMind Great work! Thats impressive!

Nathan Wilbanks9 months ago

@GoogleDeepMind THIS IS SO COOL!!!! you inspired me to try something similar using topical data from @NASA <3

Patrick Loeber9 months ago

@GoogleDeepMind love this!

ruban9 months ago

@GoogleDeepMind ty! was my first time trying out some of gemini's stuff too. everything went really smooth

Brian Chew9 months ago

@GoogleDeepMind crazy fun project!

ruban9 months ago

@GoogleDeepMind yes ser! see ya at the next one

Karthik Nagapuri9 months ago

@GoogleDeepMind by far super crazy project I have ever seen developed in short time ruhan. I really loved the way you presented, mad respect +++

Ruins9 months ago

@threejs @GoogleDeepMind I saw @dpoxley working on something similar?

𝗿𝗮𝗺𝗮𝗸𝗿𝘂𝘀𝗵𝗻𝗮— 𝗲/𝗮𝗰𝗰9 months ago

@GoogleDeepMind Congrats 🙌 looks like a fun project.

Gorka Games9 months ago

@GoogleDeepMind This is so good

gorb 🏝️9 months ago

@GoogleDeepMind Congrats man you're so impressive

ruban9 months ago

aww man, coming from you!! ty

Valmik Nahata9 months ago

@GoogleDeepMind Incredible work

flowstate9 months ago

@GoogleDeepMind This is insanely good

Chukwumaihe Onyeama || Data Analyst9 months ago

@GoogleDeepMind @CodeWithKyrian

Viviennn9 months ago

@GoogleDeepMind insane!

Danish.js9 months ago

@GoogleDeepMind Wow, very interesting

Stefan H. P. Schörling9 months ago

@GoogleDeepMind Wow… dont stop, follow the urge to combine, create and innovate! 🙌🏻👏🏻🤩

Walter Tay9 months ago

@GoogleDeepMind damn this is cool

ruban8 months ago

thank u walter!

start9 months ago

@GoogleDeepMind wow, just wow!

Simon Puxley9 months ago

@GoogleDeepMind Love it!

Døzie9 months ago

@GoogleDeepMind cool

cat ✩9 months ago

@GoogleDeepMind oh this is really cool!

ruban8 months ago

xie xie mei nu

Saïd Aitmbarek9 months ago

@GoogleDeepMind brilliant demo!

Anish9 months ago

@GoogleDeepMind Woohoo, congrats!!!

Ronit Kapar9 months ago

@GoogleDeepMind 😲😲

Christopher R Wright9 months ago

@GoogleDeepMind Looks like @levelsio needs to up his game.

call me gb9 months ago

@GoogleDeepMind this is stunning

Mr Rabbar9 months ago

@GoogleDeepMind How you managed the topography 3d?

ruban8 months ago

@threejs !!

Shivam Shaw9 months ago

@GoogleDeepMind Awesome man!

Bill G.8 months ago

@GoogleDeepMind Congratulations on your achievement. I have sent you a message regarding your projects. Please take a look. Thank you.

Angel9 months ago

@GoogleDeepMind really cool!

David Perez9 months ago

@GoogleDeepMind 😮‍💨

Related Videos

Vibe coding with AI Studio is so addictive! I built an AI Hair Stylist Agent that: > find the best haircut by looking my face > generates the after images using nano banana > lets me edit it live with the live API > find nearby salons using google maps Built in just 5 mins!

Vibe coding with AI Studio is so addictive! I built an AI Hair Stylist Agent that: > find the best haircut by looking my face > generates the after images using nano banana > lets me edit it live with the live API > find nearby salons using google maps Built in just 5 mins!

Shubham Saboo

46,658 views • 11 months ago

What could be better than a portal?! A portal that lets you switch between point clouds and 3D Gaussian Splats. Built a web-based 3D Gaussian Splat viewer with SparkJS, letting me freely fly through the three locations I just captured using the #PortalCam. #GaussianSplatting

What could be better than a portal?! A portal that lets you switch between point clouds and 3D Gaussian Splats. Built a web-based 3D Gaussian Splat viewer with SparkJS, letting me freely fly through the three locations I just captured using the #PortalCam. #GaussianSplatting

Hugues Bruyère

28,386 views • 8 months ago

Google released image creation and editing directly inside Gemini Live, allowing users to generate or modify images in real time while using the Gemini app. The feature works through live camera sharing, so users can show Gemini what they are looking at and ask it to create, adjust, or explain visuals on the spot.

Google released image creation and editing directly inside Gemini Live, allowing users to generate or modify images in real time while using the Gemini app. The feature works through live camera sharing, so users can show Gemini what they are looking at and ask it to create, adjust, or explain visuals on the spot.

Wes Roth

28,619 views • 4 months ago

First ever live demo of Samsung’s mixed reality headset running Android XR! Gemini AI built right in, the Google apps you know and love with a very intuitive UX. Also cool to see Google maps immersive view playing a key role which I cofounded & led product for while at Google!

First ever live demo of Samsung’s mixed reality headset running Android XR! Gemini AI built right in, the Google apps you know and love with a very intuitive UX. Also cool to see Google maps immersive view playing a key role which I cofounded & led product for while at Google!

Bilawal Sidhu

160,419 views • 1 year ago

The Google #HomeSpeaker is here! Brilliant 360° sound meets Gemini magic. Gemini Live lets you get expert help, chat naturally, and brainstorm ideas. Plus, you can control multiple smart home devices in a single ask.¹ Learn more:

The Google #HomeSpeaker is here! Brilliant 360° sound meets Gemini magic. Gemini Live lets you get expert help, chat naturally, and brainstorm ideas. Plus, you can control multiple smart home devices in a single ask.¹ Learn more:

Google Home

33,573 views • 3 months ago

Built this in 2 hours … lol 🫣 You can load your 3D architecture model, drop it anywhere on Google Maps, and render it at real locations…from any perspective you want. Day and night. All browser-based. Shoutout to Google AI Studio and Logan Kilpatrick Gemini 3.1 pro Preview is finally back on track after 3 rough weeks 🦾 Totally worth the wait though. My clients are gonna love this one. And I’m only 2 hours into the project. Wild Google Gemini Three.js Elon Musk Google Maps el.cine Kris Kashtanova

Built this in 2 hours … lol 🫣 You can load your 3D architecture model, drop it anywhere on Google Maps, and render it at real locations…from any perspective you want. Day and night. All browser-based. Shoutout to Google AI Studio and Logan Kilpatrick Gemini 3.1 pro Preview is finally back on track after 3 rough weeks 🦾 Totally worth the wait though. My clients are gonna love this one. And I’m only 2 hours into the project. Wild Google Gemini Three.js Elon Musk Google Maps el.cine Kris Kashtanova

Miles Dyson

94,339 views • 7 months ago

Working on a 3d purchase visual. It converts 2d asset images from our live trending-sales wall into 3d models during runtime There's some extra effects with tweening & tilting that I show at the end - excited to start testing this in production Clip It #RobloxDev

Working on a 3d purchase visual. It converts 2d asset images from our live trending-sales wall into 3d models during runtime There's some extra effects with tweening & tilting that I show at the end - excited to start testing this in production Clip It #RobloxDev

ScriptOn

23,936 views • 1 year ago

We built a web app that lets you fly a spaceship through a 3D constellation of music - powered by our Lyria RealTime model. 🎶 Space DJ is an interactive visualization where every star represents a different music genre. As you explore, your path is translated into prompts for the API, creating a continuously evolving soundtrack. ↓

We built a web app that lets you fly a spaceship through a 3D constellation of music - powered by our Lyria RealTime model. 🎶 Space DJ is an interactive visualization where every star represents a different music genre. As you explore, your path is translated into prompts for the API, creating a continuously evolving soundtrack. ↓

Google DeepMind

280,490 views • 11 months ago

Here's a demo of the gpt-4-vision API that I built in Bubble in 30 min. It takes a URL, converts it to an image, and sends it through the Vision API to respond with custom landing page optimization suggestions.

Here's a demo of the gpt-4-vision API that I built in Bubble in 30 min. It takes a URL, converts it to an image, and sends it through the Vision API to respond with custom landing page optimization suggestions.

Seth Kramer

954,041 views • 2 years ago

PanoWorld. An interesting way to use Qwen-Edit. It converts 2D floor plans into photorealistic, consistent VR home tours. Great for real estate and interior designers. It lets you walk through a home that hasn’t been built or furnished yet. Ensures seamless 360 views via CPRoPE

PanoWorld. An interesting way to use Qwen-Edit. It converts 2D floor plans into photorealistic, consistent VR home tours. Great for real estate and interior designers. It lets you walk through a home that hasn’t been built or furnished yet. Ensures seamless 360 views via CPRoPE

Wildminder

20,448 views • 4 months ago

🗣️✨ Speak your vibes into existence with Gemini 3.5 Transcribe The latest audio model is built for apps that need live transcription and quick visual prototyping. Watch genevieveh@ turn spoken ideas into a dynamic mood board using Gemini 3.5 Transcribe on the Live API. The model maps speech to user intent to create prompts that trigger live image generation and editing with Nano Banana 2 Lite:

🗣️✨ Speak your vibes into existence with Gemini 3.5 Transcribe The latest audio model is built for apps that need live transcription and quick visual prototyping. Watch genevieveh@ turn spoken ideas into a dynamic mood board using Gemini 3.5 Transcribe on the Live API. The model maps speech to user intent to create prompts that trigger live image generation and editing with Nano Banana 2 Lite:

Google for Developers

36,074 views • 1 month ago

had a raspberry pi laying around and built an ai wearable called insight at Google x MHacks hackathon this weekend. insight uses gemini 1.5 pro to answer questions based on what you see and hear, and it remembers those memories for you. repo in comments

had a raspberry pi laying around and built an ai wearable called insight at Google x MHacks hackathon this weekend. insight uses gemini 1.5 pro to answer questions based on what you see and hear, and it remembers those memories for you. repo in comments

Advait Paliwal

672,245 views • 2 years ago

🧵 New feature drops 🧵 Navigation in Google Maps is getting a powerful boost with Gemini. Ask for whatever you need — like planning a stop at a restaurant or parking details — and Gemini handles the rest. Rolling out in the coming weeks on Android and iOS everywhere Gemini is available, with Android Auto on the way.

🧵 New feature drops 🧵 Navigation in Google Maps is getting a powerful boost with Gemini. Ask for whatever you need — like planning a stop at a restaurant or parking details — and Gemini handles the rest. Rolling out in the coming weeks on Android and iOS everywhere Gemini is available, with Android Auto on the way.

Google Maps

225,431 views • 11 months ago

Here’s how AI Mode and Google Maps’ Ask Maps can help you find and book the right table at the right restaurant right when you want it. Here’s how: 1️⃣ Describe all your needs — including details about your group size, ideal vibe and time and dietary preferences — in AI Mode in Search or Google Maps’ Ask Maps. 2️⃣ We’ll search across multiple reservation platforms and websites to find real-time availability for options that match your criteria. 3️⃣ From there, Ask Maps and AI Mode will present a curated list of restaurants to choose from with direct links to finalize your bookings through partners like OpenTable or Resy.

Here’s how AI Mode and Google Maps’ Ask Maps can help you find and book the right table at the right restaurant right when you want it. Here’s how: 1️⃣ Describe all your needs — including details about your group size, ideal vibe and time and dietary preferences — in AI Mode in Search or Google Maps’ Ask Maps. 2️⃣ We’ll search across multiple reservation platforms and websites to find real-time availability for options that match your criteria. 3️⃣ From there, Ask Maps and AI Mode will present a curated list of restaurants to choose from with direct links to finalize your bookings through partners like OpenTable or Resy.

Google

114,521 views • 5 months ago

Lovable (Lovable) Co-Founder Fabian Hedin told us in the end they want to get to a place where any business built on Lovable is more successful than if it would be built elsewhere: "As opposed to these developer tools that help you output code. The output of Lovable is not code." "Sure, we write code for you and we handle that for you, but you're not looking at code, right? You're looking at the product that you're building...looking at the business that you're building." "In the end, getting to a place where any business that is built on Lovable is more successful than if it would be built elsewhere."

Lovable (Lovable) Co-Founder Fabian Hedin told us in the end they want to get to a place where any business built on Lovable is more successful than if it would be built elsewhere: "As opposed to these developer tools that help you output code. The output of Lovable is not code." "Sure, we write code for you and we handle that for you, but you're not looking at code, right? You're looking at the product that you're building...looking at the business that you're building." "In the end, getting to a place where any business that is built on Lovable is more successful than if it would be built elsewhere."

etn.

10,405 views • 1 month ago

Impeccable creator Paul Bakaus says AI should be cognitive delegation, not cognitive surrender: "Cognitive delegation is, I'm using Google Maps, and Google Maps tells me where I can go as quickly as possible." "But what if I let Google Maps decide where I want to go to? Now I kind of cognitive surrender to the application, and I think that's very true for LLMs if you're not careful." "You prompt something, and then it creates a beautiful plan, and then it's eight pages long. You're not going to read through that plan. You're going to scroll through that plan and skim it, and it's like, 'I guess the model knows what it's doing.'" "I think delegating to the model is great, but preserving that point of view, making sure that you're still the one driving is also really important." Paul Bakaus

Impeccable creator Paul Bakaus says AI should be cognitive delegation, not cognitive surrender: "Cognitive delegation is, I'm using Google Maps, and Google Maps tells me where I can go as quickly as possible." "But what if I let Google Maps decide where I want to go to? Now I kind of cognitive surrender to the application, and I think that's very true for LLMs if you're not careful." "You prompt something, and then it creates a beautiful plan, and then it's eight pages long. You're not going to read through that plan. You're going to scroll through that plan and skim it, and it's like, 'I guess the model knows what it's doing.'" "I think delegating to the model is great, but preserving that point of view, making sure that you're still the one driving is also really important." Paul Bakaus

a16z

80,185 views • 3 months ago

NEW: Google just launched a new laptop category for the AI era. Googlebook is coming this fall with Gemini built into the cursor, desktop, and Android phone connection. • Magic Pointer lets you select anything on screen and ask Gemini about it • Create My Widget builds custom desktop widgets from a prompt • Cast My Apps opens your Android phone apps on the laptop • Quick Access lets phone files show up like they live on your laptop • built with partners including Acer, Asus, Dell, HP, and Lenovo

NEW: Google just launched a new laptop category for the AI era. Googlebook is coming this fall with Gemini built into the cursor, desktop, and Android phone connection. • Magic Pointer lets you select anything on screen and ask Gemini about it • Create My Widget builds custom desktop widgets from a prompt • Cast My Apps opens your Android phone apps on the laptop • Quick Access lets phone files show up like they live on your laptop • built with partners including Acer, Asus, Dell, HP, and Lenovo

Ritwik Pavan

81,283 views • 5 months ago

That is the easiest way to chat with a complete Github Repository!👀 Replace "github" with "gitingest" in the url, and you get the whole repo as a single string, paste into AI studio and use Google DeepMind Gemini 2.0 Flash Million Token Context video to ask questions! 🤯 Here is how you can chat with the whole python SDK docs. ⬇️

That is the easiest way to chat with a complete Github Repository!👀 Replace "github" with "gitingest" in the url, and you get the whole repo as a single string, paste into AI studio and use Google DeepMind Gemini 2.0 Flash Million Token Context video to ask questions! 🤯 Here is how you can chat with the whole python SDK docs. ⬇️

Philipp Schmid

97,475 views • 1 year ago

5️⃣ Talk it out with Gemini Live Today, we’re bringing Deep Research into Gemini Live so you can launch comprehensive, multi-step research reports with your voice 🗣️✨ Using Deep Research, you can ask Gemini Live to research any topic, then step away, lock your screen, or switch tasks. Gemini works in the background and sends a notification when your report is ready. You can chat through the results, ask follow-up questions, and more. Learn more and sign up for your free student plan for one year →

5️⃣ Talk it out with Gemini Live Today, we’re bringing Deep Research into Gemini Live so you can launch comprehensive, multi-step research reports with your voice 🗣️✨ Using Deep Research, you can ask Gemini Live to research any topic, then step away, lock your screen, or switch tasks. Gemini works in the background and sends a notification when your report is ready. You can chat through the results, ask follow-up questions, and more. Learn more and sign up for your free student plan for one year →

Google

25,732 views • 1 month ago

i built an app that converts any space into a digital clone in minutes as the founder of Teleport - the only iphone app that can capture high-quality 360° panoramas - i already had the perfect input when World Labs released their 3d reconstruction api 📍 first test - a co-working space in chiang mai 🇹🇭 the flow: 1. capture 16 ultra-wide photos 2. stitch into a 360° equirectangular image 3. reconstruct a fully navigable 3d environment via World Labs api there’s something profound about exploring these 3d worlds. it brings you back in a way photos never could.

i built an app that converts any space into a digital clone in minutes as the founder of Teleport - the only iphone app that can capture high-quality 360° panoramas - i already had the perfect input when World Labs released their 3d reconstruction api 📍 first test - a co-working space in chiang mai 🇹🇭 the flow: 1. capture 16 ultra-wide photos 2. stitch into a 360° equirectangular image 3. reconstruct a fully navigable 3d environment via World Labs api there’s something profound about exploring these 3d worlds. it brings you back in a way photos never could.

Martin Maly

5,158,816 views • 8 months ago