Google recently announced in a blog post that the code for their "semantic image segmentation", the technology behind the Pixel 2 and Pixel 2 XL's portrait mode, is now open source.
Semantic image segmentation is the process of assigning a label (e.g. road, sky, person, dog) to each and every pixel in an image, allowing subject and background to be distinguished from one another. The camera can then blur the background accordingly now that it has been identified.
⟦PH0X⟆ ginagawa ang open source na semantic image segmentation model ay nagbubukas ng daan para sa ibang mga tagagawa ng telepono na samantalahin ito, posibleng alisin ang pangangailangan nilang gumamit ng pangalawang kamera upang mag‑map ng lalim. Tulad ng alam natin, ang ⟦PH0X⟆ Pixel 2 ay may kamangha‑manghang portrait mode, at nagagawa ito gamit lamang isang lente ng kamera.
Ang portrait mode ay isa lamang na aplikasyon ng semantic image segmentation model. Maaari mong tingnan ang blog post ni Google para sa mas detalyadong paliwanag kung paano ito gumagana.
0 Comments
Leave a Reply