iOS 11 camera features may include scene recognition

Smartphones may have effectively killed off dedicated point-and-shoot cameras, but Apple is looking to them for inspiration with iOS 11. Developers have dug through beta firmware for the HomePod, and tucked inside the code for Apple’s smart speaker, there are hints that the next version of its mobile OS will feature something called “SmartCam.” iOS 11 (or the next iPhone) will have something called SmartCam. It will tune camera settings based on the scene it detects pic.twitter.com/7duyvh5Ecj — Guilherme Rambo (@_inside) August 2, 2017 If you’ve ever used a point-and-shoot camera, the feature should sound pretty familiar: different scene modes and photo settings depending on what you’re shooting. So, one each for fireworks, foliage, pets, skies, snow, sports and others, as SlashGear notes. There’s even one for documents. The “smart” in its name suggests that maybe machine learning will play a role here as well, potentially analyzing the scene for you and picking the best settings. This might not use machine learning to improve photography a la what Google does with the Pixel , but it could make Apple’s woefully basic camera app a little more full featured. Whether this will be exclusive to Apple’s next round of mobile hardware — whenever it’s announced — or if it’ll apply to legacy handsets too is hard to tell. Via: SlashGear Source: Guilherme Rambo (Twitter)

View article:
iOS 11 camera features may include scene recognition

AI film editor can cut scenes in seconds to suit your style

AI has won at Go and done a few other cool things, but so far it’s been mighty unimpressive at harder tasks like customers service , Twitter engagement and script writing . However, a new algorithm from researchers at Stanford and Adobe has shown it’s pretty damn good at video dialogue editing, something that requires artistry, skill and considerable time. The bot not only removes the drudgery, but can edit clips using multiple film styles to suit the project. First of all, the system can organize “takes” and match them to lines of dialogue from the script. It can also do voice, face and emotion recognition to encode the type of shot, intensity of the actor’s feelings, camera framing and other things. Since directors can shoot up to 10 takes per scene (or way more , in the case of auteurs like Stanley Kubrick), that alone can save hours. However, the real power of the system is doing “idiom” editing based on the rules of film language. For instance, many scenes start with a wide “establishing” shot so that the viewer knows where they are. You can also use leisurely or fast pacing, emphasize a certain character, intensify emotions or keep shot types (like wide or closeup) consistent. Such idioms are generally used to best tell the story in the way the director intended. All the editor has to do is drop their preferred idioms into the system, and it will cut the scene to match automatically, following the script. In an example shown (below), the team selected “start wide” to establish the scene, “avoid jump cuts” for a cinematic (non-YouTube) style, “emphasize character” (“Stacey”) and use a faster-paced performance. The system instantly created a cut that was pretty darn watchable, closely hewing to the comedic style that the script was going for. The team then shuffled the idioms, and it generated a “YouTube” style that emphasized hyperactive pacing and jump cuts. What’s best (or worst, perhaps for professional editors) is that the algorithm was able to assemble the 71-second cut within two to three seconds and switch to a completely different style instantly. Meanwhile, it took an editor three hours to cut the same sequence by hand, counting the time it took to watch each take. The system only works for dialogue, and not action or other types of sequences. It also has no way to judge the quality of the performance, naturalism and emotional beats in take. Editors, producers and directors still have to examine all the video that was shot, so AI is not going to take those jobs away anytime soon. However it looks like it’s about ready to replace the assistant editors who organize all the materials, or at least do a good chunk of their work. More importantly, it could remove a lot of the slogging normally required to edit, and let an editor see some quick cuts based on different styles. That would leave more time for fine-tuning, where their skill and artistic talent are most crucial. Source: Stanford

See original article:
AI film editor can cut scenes in seconds to suit your style

Facebook’s new 360 cameras bring multiple perspectives to live videos

Last year, Facebook announced the Surround 360 , a 360-degree camera that can capture footage in 3D and then render it online via specially designed software. But it wasn’t for sale. Instead, the company used it as a reference design for others to create 3D 360 content, even going so far as to open source it on Github later that summer. As good as the camera was, though, it still didn’t deliver the full VR experience. That’s why Facebook is introducing two more 360-degree cameras at this year’s F8 : the x24 and x6. The difference: These cameras can shoot in six degrees of freedom, which promises to make the 360 footage more immersive than before. The x24 is so named because it has 24 cameras; the x6, meanwhile, has — you guessed it — six cameras. While the x24 looks like a giant beach ball with many eyes, the x6 is shaped more like a tennis ball, which makes for a less intimidating look. Both are designed for professional content creators, but the x6 is obviously meant to be a smaller, lighter and cheaper version. Both the x24 and the x6 are part of the Surround 360 family. And, as with version one (which is now called the Surround 360 Open Edition), Facebook doesn’t plan on selling the cameras themselves. Instead, Facebook plans to license the x24 and x6 designs to a “select group of commercial partners.” Still, the versions you see in the images here were prototyped in Facebook’s on-site hardware lab (cunningly called Area 404) using off-the-shelf components. The x24 was made in partnership with FLIR, a company mostly known for its thermal imaging cameras, while the x6 prototype was made entirely in-house. But before we get into all of that, let’s talk a little bit about what sets these cameras apart from normal 360 ones. With a traditional fixed camera, you see the world through its fixed lens. So if you’re viewing this content (also known as stereoscopic 360) in a VR headset and you decide to move around, the world stays still as you move, which is not what it would look like in the real world. This makes the experience pretty uncomfortable and takes you out of the scene. It becomes less immersive. With content that’s shot with six degrees of freedom, however, this is no longer an issue. You can move your head to a position where the camera never was, and still view the world as if you were actually there. Move your head from side to side, forwards and backwards, and the camera is smart enough to reconstruct what the view looks like from different angles. All of this is due to some special software that Facebook has created, along with the carefully designed pattern of the cameras. According to Brian Cabral, Facebook’s Engineering Director, it’s an “optimal pattern” to get as much information as possible. I had the opportunity to have a look at a couple of different videos shot with the x24 at Facebook’s headquarters (Using the Oculus Rift, of course). One was of a scene shot in the California Academy of Sciences, specifically at the underwater tunnel in the Steinhart Aquarium. I was surprised to see that the view of the camera would follow my own as I tilted my head from left to right and even when I crouched down on the floor. I could even step to the side and look “through” where the camera was, as if it wasn’t there at all. If the video was shot through a traditional 360 camera, it’s likely that I would see the camera tripod if I looked down. But with the x24, I just saw the floor, as if I was a disembodied ghost floating around. Another wonderful thing about videos shot with six degrees of freedom is that each pixel has depth. Each pixel is literally in 3D. This a breakthrough for VR content creators, and opens up a world of possibilities in visual effects editing. This means that you can add 3D effects to live action footage, a feat that usually would have required a green screen. I saw this demonstrated in the other video, which was of a scene shot on the roof of one of Facebook’s buildings. Facebook along with Otoy, a Los Angeles-based cloud rendering company, were able to actually add effects to the scene. Examples include floating butterflies, which wafted around when I swiped at them with a Touch controller. They also did a visual trick where I could step “outside” of the scene and encapsulate the entire video in a snow globe. All of this is possible because of the layers of depth that the footage provides. That’s not to say there weren’t bugs. The video footage I saw had shimmering around the edges, which Cabral said is basically a flaw in the software that they’re working to fix. Plus, the camera is unable to see what’s behind people, so there’s a tiny bit of streaking along the edges. Still, there’s lots of potential with this kind of content. “This is a new kind of media in video and immersive experiences, ” said Eric Cheng, Facebook’s head of Immersive Media, who was previously the Director of Photography at Lytro. “Six degrees of freedom has traditionally been done in gaming and VR, but not in live action.” Cheng says that many content creators have told him that they’ve been waiting for a way to bridge live action into these “volumetric editing experiences.” Indeed, that’s partly why Facebook is partnering with a lot of post-production companies like Adobe, Foundry and Otoy in order to develop an editing workflow with these cameras. “Think of these cameras as content acquisition tools for content creators, ” said Cheng. But what about other cameras, like Lytro’s Immerge for example? “There’s a large continuum of these things, ” said Cabral. “Lytro sits at the very very high-end.” It’s also not nearly as portable as both the x24 and x6, which are both designed for a much more flexible and nimble approach to VR capture. As for when cameras like these will make their way down to the consumer level, well, Facebook says that will come in future generations. “That’s the long arc of where we’re going with this, ” said CTO Mike Schroepfer. “Our goal is simple: We want more people producing awesome, immersive 360 and 3D content, ” said Schroepfer. “We want to bring people up the immersion curve. We want to be developing the gold standard and say this is where we’re shooting for.” Click here to catch up on the latest news from F8 2017!

See more here:
Facebook’s new 360 cameras bring multiple perspectives to live videos