It’s got words like pixel, recognise, body part and ”probability distribution” for us to read and nod along too. Surely you’ve heard of ‘multiple centroid proposals’?
”Each pixel of the player segmentation is fed into a machine learning system that’s been trained to recognize parts of the human body,” detailed Microsoft.
”This gives us a probability distribution of the likelihood that a given pixel belongs to a given body part. For example, one pixel may have an 80% chance of belonging to a foot, a 60% chance of belonging to a leg, and a 40% chance of belonging to the chest.”
”It might make sense initially to keep the most probable proposal and throw out the rest, but that would be a bit premature.” Of course, stop patronising us.
”Rather, we send all of these possibilities (called multiple centroid proposals) down the rest of the pipeline and delay this judgment call until the very end.” To expand your learning why not check out the Xbox Engineering Blog for more? Knowledge is power, but then so is money… and time is money - quite the conundrum.
