(2017-09-11) Why Is Arkit Better Than The Alternatives Super Ventures Blog Medium

Why is ARKit better than the alternatives? Technically ARKit is a Visual Inertial Odometry (VIO) system, with some simple 2D plane detection. VIO means that the software tracks your position in space (your 6dof pose) in real-time ie your pose is recalculated in between every frame refresh on your display

Just like your odometer in your car tracks the distance the car has traveled, the VIO system tracks the distance that your iPhone has traveled in 6D space. 6D means 3D of xyz motion (translation), plus 3D of pitch/yaw/roll (rotation).

The second main piece of ARKit is simple plane detection. This is needed so you have “the ground” to place your content on, otherwise it would look like it’s floating horribly in space

SLAM as a pretty broad term, like say "multi-media".

Two “mysteries” of ARKit are “how do you get 3D from a single lens?” and “how do you get metric scale (like in that tape measure demo)?”. The secret here is to have really good IMU error removal (ie making the Dead Reckoning guess highly accurate)

What about Tango & Hololens & Vuforia etc?

The answer is that ARKit isn’t really any better than Hololens (I’d even argue that Hololens’ tracker is the best on the market) but Hololens hardware isn’t widely available.

Google also could easily have shipped Tango’s VIO system in a mass market Android phone over 12 months ago, but they also chose not to.

So ultimately the reason ARKit is better is because Apple could afford to do the work to tightly couple the VIO algorithms to the sensors and spend a lot of time calibrating them to eliminate errors / uncertainty in the pose calculations.

There are a number of startups working on tracking systems, Augmented Pixels has one that performs well, but at the end of the day any VIO system needs the hardware modelling & calibration to compete.

I’m a Developer, what should I use & why? a.k.a. Burying the lede

This is a REALLY STEEP learning curve. Bigger than from web to mobile or from mobile to VR

I would encourage devs not to be afraid of building Novelty apps. Fart apps were the first hit on smartphones… also it’s very challenging to find use-cases that give Utility via AR on handheld see-through form-factor hardware

Its a very small world. Not many people can build these systems well.

Performance is Statistics

For this reason NEVER trust a demo of an AR App, especially if it’s been shown to be amazing on YouTube

Integrating Hardware & Software

To build a great inertial tracking system needs experienced engineers. Unfortunately there are only about 20 engineers on earth with the necessary skills and experience, and most of them work building cruise missile tracking systems, or mars rover navigation systems

Optical Calibration

Inertial Calibration

The Future of Tracking

The Future of AR Computer Vision

The future of other parts of AR