Gadgetory

my name is Timothy night I'm an engineering director at Google for the Android camera team okay so first on the fundamentals so image quality video quality speed shutter latency time to open we double down on all those right so everywhere better than last year you know better photos better videos on top of that we added some new features so we added OS for even crisper photos and more stable videos ok the portrait mode we added motion photos face retouching I think the experience is really evolved so the technique we use is we capture a burst of photos and then we combine them together in software it does make a really high dynamic range high quality final photograph so with OS now every single frame in that burst is sharper and cleaner so the final result is even sharper and cleaner than been before and in video mode in video mode so a problem that if you don't have OES is that if there's motion blur within a frame you got a little bit of a wobbling so jiggly look to the video but by running optical stabilization within video recording - it's even smoother we get rid of that at motion shake and it's now like a more stable feel we're capturing much darker versions of the scene where the highlights are not blurred out this guy is still blue and then we do some very sophisticated noise reduction by combining frames together and then apply tone mapping to get to the final rendition so you're able to preserve the highlights and the blue skies and also in the dark areas we see detail in the shadows so they're actually two techniques the first technique is machine learning so by training a model on the million images like a lot of images we're able to understand the foreground background segmentation and you know on both the front and rear camera you know do you know a really nice background blur additionally for the rear camera we have a special sense of Penelope referred to as dual pixel where every single pixel has both a left and a right off and conceptually Alesi you have two slightly different viewpoints of the scene as if you like move your head a little bit left and right and that is enough to give you actually a depth map of the scene and combining that with the machine learning model we can get an even more accurate portrait photo as well as photos of things that part people there are a lot of dual cameras on the market you know they may not all be that great dual camera is a you know it brings a lot of trade-offs with it you know for example takes more space and maybe the battery smaller you know often the second camera is really not very good in low light and for us the light is super important because smaller pixels in a shallower sorry a narrower aperture but in the end I think that the you know image quality that the get quality the capabilities wanted to bring to the table were really like I said a single camera experience and I believe that we we met that goal you know best photos in the world best food is in the world fastest captured saying Foss is open time it's hard to complain about that