ARKit's and RealityKit's Body Motion Capture really takes advantage when you track body using a device with a LiDAR Scanner. And Apple engineers explicitly say about it in Advanced Scene Understanding in AR video (time: 1:30). But there's no guarantee that LiDAR will help you improve a quality of MoCap in your particular case. The only advice – just try it.
What if creating a stunning, high-performing app was as simple as sketching ideas on paper? At WWDC25, Apple introduced PaperKit, a new framework poised to redefine how developers approach app ...
RealityKit vs ARKit The RealityKit's ARSession is based on the ARKit's AR session, but has its own add-ons that allow you to automate the tracking of several anchors' types. However, the difference between two is that RealityKit has engines for rendering, physics and animation. And do not forget that ARKit is umbrella containing SceneKit and SpriteKit.
The framework supports the same type of transform matrices as SceneKit, RealityKit and Metal. iOS ARKit's collaboration with NearbyInteraction framework allows users to acquire the precise position of nearby devices (you can get distance, direction and IDs) with U1+ chips, using the visual capabilities of ARKit. iOS ARKit can capture 4K HDR video.
I'm in the process of learning both ARKit and Scenekit concurrently, and it's been a bit of a challenge. With a ARWorldTrackingSessionConfiguration session created, I was wondering if anyone knew of a way to get the position of the user's 'camera' in the scene session.
However I think it would be easier If I had access to the mesh directly, and filter out the nodes closest to the camera. So my question is: How do I get access to the mesh generated by ARKit?