Everyone's building AR filters and calling it "computer vision magic." Almost nobody's asking wha...Everyone's building AR filters and calling it "computer vision magic." Almost nobody's asking wha...
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Everyone's building AR filters and calling it "computer vision magic." Almost nobody's asking what's actually happening underneath — that most of these effects are just clever masking, not detection.
Here's proof. I built an invisibility cloak that runs entirely in the browser, no green screen, no chroma key, no model training. https://github.com/AnuragNagare/Ghost-frame
Julian's avatar
Strong example of why the distinction between masking and detection matters. A useful next benchmark would be robustness under lighting changes and moving backgrounds, with latency and failure cases shown alongside the effect. That would make the trade-offs very clear for browser-based workflows.
Anurag's avatar
I agree
Abdullah's avatar
Eroglu Studios logo
Good point and nice work!
Anurag's avatar
Thank you 😊
Back to feed
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started