getToTheChopin

Thank you! I spent a lot of time tuning the synth parameters in tonejs to try to get something I was happy with.

The scales are based on the Japanese "in" pentatonic scale (sometimes called the Sakura scale), which I find really pretty.

here's the demo video on youtube as well: https://youtu.be/XBn5F72aIbg

thank you. I thought of this on a roadtrip and was very keen to start building it when I got home.

This is a computer vision experiment, using voice + hand gestures to control a shader animation.

This uses a liquid Chladni pattern, with controls for color and wave frequency / amplitude.

Created using threejs, mediapipe computer vision, and web speech API.

Thank you for the feedback. I'll continue to work on it!

I'll try it, thank you! I separated them into completely different interaction modes to avoid misfires, but there's definitely room for efficiencies

It's a shame that computer vision tech like Leap / Eyetoy / Kinect didn't have lasting power. So much fun to build with

I made a demo game where you need to dodge the evil bouncing DVD logo by moving your body: https://x.com/measure_plan/status/1924830500541157570

I'm working on a couple other body movement concepts and hope to share soon :)

Good points, maybe a second camera (phone?) pointed downwards at the tabletop would be good for that. Then the user can rest their hands in a "normal" position.

Thank you for the feedback!

yes I'd love to go further with this concept so that 3D / CAD designers could easily present their models during video calls.

thank you!

Sorry about that, the instructions need to be improved.

Does this video demo help?

https://x.com/measure_plan/status/1929900748235550912

If it makes it clearer, I'll upload it to the github repo directly

Here's a quick video demo showing how it works: https://x.com/measure_plan/status/1929900748235550912

I'm working on it now! thank you

3D model control (move, rotate, scale, animate) using hand gestures and voice commands, running in real-time in the browser

Created with threejs, mediapipe computer vision, and web speech API

3D model from Quaternius

Here's the live demo if you want to try: https://rosebud.ai/p/93986db5-4d99-437f-9e8b-c8d742e131da

Any feedback would be appreciated!

Created using threejs, mediapipe computer vision, web speech API, and Vasco Asturiano's 3D-force-graph library

I made a game. It's called PC versus Mac.

Use your hands to show support for Bill Gates or Steve Jobs.

Created with threejs and mediapipe computer vision.

Game link: https://rosebud.ai/p/8bd0a69f-f009-4af4-b3c6-9e60f356e98f

Recreating the Macrodata Refinement game from Severance.

Built with threejs, rosebud AI, mediapipe computer vision for hand tracking, and tone.js for sound effects.

I haven't added any patterns or number puzzles to solve yet, any ideas?

To try the game demo: https://rosebud.ai/p/5f611cac-59e5-44c5-8807-8b41b7c4b6e2

Using speech recognition to toggle between drag / rotate / zoom interactions, and hand gestures to move the nodes of the graph

Created with threejs, rosebud AI, mediapipe computer vision, web speech API, and Vasco Asturiano's 3D-force-graph library

Runs in real-time in the browser using a regular laptop + webcam

Live demo (works best on chrome desktop): https://rosebud.ai/p/557dbe2b-b037-42df-a137-249f8a57341d

Quick tech demo powered by a regular laptop webcam, cesiumjs, and mediapipe computer vision.

Runs in real-time in the browser.

I made a website. It's called "am i a banana?"

it uses your camera and detects bananas in real-time (using COCO dataset / tensor flow).

Demo video: https://x.com/measure_plan/status/1919772316755542200

that's it. have fun!

Ah! Can you let me know what device / browser you were using? Do you remember what type of image you tried to upload (png, JPEG, etc.)?

thank you! Let me know if you have any suggestions after you try it

You can't do a loop right now, but I'll try to add that. Would be very cool

Not right now unfortunately, but I'll try to add this

Thank you! Right now you can open the controls at the top-right and then adjust the width / height of the canvas.

I'll try to make it easier with a single click

Sorry about that -- yes it was an oversight on my part.

I had included this small credit in the commentary on the website: "The song used is Fahrenheit Fair Enough by Telefon Tel Aviv."

This isn't enough -- I've pushed a changed showing a song credit at the bottom-left of the canvas that appears when you first load the page.

I also added a song credit in the github readme.

Telefon Tel Aviv is one of my favourite bands, I hope they get more listeners!

This is great feedback, thank you for playing and let me know these comments.

Yes I definitely need to improve the mechanic of pausing / restarting the game when hand tracking is lost. I'll try to implement it the way you suggested.

Cheers!

Thank you! Mediapipe is quite neat, I'd like to try some other projects with their hand tracking / face tracking

Thanks for playing! Good feedback. I'll try to improve the mobile performance, the fps seems lower vs. Destkop at the moment

I noticed this in Seoul and Busan -- almost everyone was wearing similar outfits, predominantly in Beige / White / Black.