Deep-learning technique reveals “invisible” objects in the dark

As machine learning techniques become part of our everyday use cases, it seems almost magical and open a new door of possibilities.

As smarts started becoming powerful, and manufacturers started pushing more features into them. We in recent years, almost every manufacturer was focused on pushing more pixel and multiple lenes to improve quality of pictures captured from a phone camera. Recently when Pixel 3, we can see how they use computational photography (which heavily uses ML techniques) to improve photo quality especially in low light conditions. DSLR enthusiasts would have never thought it would be possible to have such a high detail photo capture capability with such small lenses and yet we have something that almost looks like DSLR quality.

Check out the below article for more on how deep learning is used to find objects in complete darkness.

Small imperfections in a wine glass or tiny creases in a contact lens can be tricky to make out, even in good light. In almost total darkness, images of such transparent features or objects are nearly impossible to decipher. But now, engineers at MIT have developed a technique that […]

Click here to view original web page at Deep-learning technique reveals “invisible” objects in the dark

Leave a comment

Your email address will not be published. Required fields are marked *

Christian Miller Authentic Jersey