Click-to-segment lab

Click an object in your photograph. SlimSAM proposes a mask and reuses the image embedding for the next click.

How this experiment works

SlimSAM separates image encoding from a point-conditioned mask decoder. The highest predicted IoU candidate is displayed.

What it does not prove

A mask is a prediction. One positive point can select the wrong object or an entire region.

Try this challenge

Click the edge of an object, then its centre. How does the chosen region change?

Related Trust Agent courses · Sources and licences

Enable JavaScript to run the experiment on your device.