The goal is to achieve precise joint tracking for clinical assessment. The Doctor is wearing the AVP and observing the Patients movement. Do you have any recommended best practices for integrating real-time joint tracking and displaying them on the patient within visionOS? We attempted to use VNHumanBodyPose3DObservation, which theoretically should work, but we are unable to display the detected joints in an Immersive Space for real-time validation. This makes it difficult for the doctor to ensure accurate tracking and if possible a photo or video of the Range of Motion assessment would be needed for the patient record. Are there alternative methods to achieve precise real-time joint tracking without requiring main camera access (com.apple.developer.arkit.main-camera-access.allow)?

Hi! I attempted to run a sample project for detecting human pose in photos, which can be found here: https://developer.apple.com/documentation/vision/detecting-human-body-poses-in-3d-with-vision The project works perfectly when run on my Macbook Pro M1, but it fails on Apple Vision Pro. After selecting the photo an endless loading screen is presented and the following output is produced in the console: Failed to initialize 2D Detection Algorithm. Failed to initialize 2D Pose Estimation Algorithm. Failed to initialize algorithm modules Network path is nil: (null) Failed to initialize 2D Detection Algorithm. Failed to initialize 2D Pose Estimation Algorithm. Failed to initialize algorithm modules Unable to perform the request: Error Domain=com.apple.Vision Code=9 "Async status object reported as failed but without an error" UserInfo={NSLocalizedDescription=Async status object reported as failed but without an error}. de-activating session 70138 after timeout It seems that VNDetectHumanBodyPose3DRequest is failing on Vision Pro for some reason. Are there any additional requirements for running Vision framework on VisionOS, that I might be missing?

I'm using ARKitSession and PlaneDetectionProvider to detect planes. I have a basics process to create an entity for each detected plane. Each one will get a random color for the material. Each plane is sized based on the bounds of the anchor provided by ARKit. let mesh = MeshResource.generatePlane( width: anchor.geometry.extent.width, depth: anchor.geometry.extent.height ) Then I'm using this to position each entity. entity.transform = Transform(matrix: anchor.originFromAnchorTransform) This seems to be the right method, but many (not all) planes are not where they should be. The sizes look OK, but the X and Y positions off. Take this large green plane on the wall. It should span the entire wall, but it is offset along the X position so that it is pushed to the left from where the center of the anchor is. When I visualize surfaces using the Xcode debugging tools, that tool reports the planes where I'd expect them to be. Can you see what I'm getting wrong here? Full code below struct Example068: View { @State var session = ARKitSession() @State private var planeAnchors: [UUID: Entity] = [:] @State private var planeColors: [UUID: Color] = [:] var body: some View { RealityView { content in } update: { content in for (_, entity) in planeAnchors { if !content.entities.contains(entity) { content.add(entity) } } } .task { try! await setupAndRunPlaneDetection() } } func setupAndRunPlaneDetection() async throws { let planeData = PlaneDetectionProvider(alignments: [.horizontal, .vertical, .slanted]) if PlaneDetectionProvider.isSupported { do { try await session.run([planeData]) for await update in planeData.anchorUpdates { switch update.event { case .added, .updated: let anchor = update.anchor if planeColors[anchor.id] == nil { planeColors[anchor.id] = generatePastelColor() } let planeEntity = createPlaneEntity(for: anchor, color: planeColors[anchor.id]!) planeAnchors[anchor.id] = planeEntity case .removed: let anchor = update.anchor planeAnchors.removeValue(forKey: anchor.id) planeColors.removeValue(forKey: anchor.id) } } } catch { print("ARKit session error \(error)") } } } private func generatePastelColor() -> Color { let hue = Double.random(in: 0...1) let saturation = Double.random(in: 0.2...0.4) let brightness = Double.random(in: 0.8...1.0) return Color(hue: hue, saturation: saturation, brightness: brightness) } private func createPlaneEntity(for anchor: PlaneAnchor, color: Color) -> Entity { let mesh = MeshResource.generatePlane( width: anchor.geometry.extent.width, depth: anchor.geometry.extent.height ) var material = PhysicallyBasedMaterial() material.baseColor.tint = UIColor(color) let entity = ModelEntity(mesh: mesh, materials: [material]) entity.transform = Transform(matrix: anchor.originFromAnchorTransform) return entity } }

In several visionOS apps, we readjust our scenes to the user's eye level (their heads). But, we have encountered issues whereby the WorldTrackingProvider returns bad/incorrect positions for the first x number of frames. See below code which you can copy paste in any Immersive Space. Relaunch the space and observe the numberOfBadWorldInfos value is inconsistent. a. what is the most reliable way to get the devices's position? b. is this indeed a bug? c. are we using worldInfo improperly? d. as a workaround, in our apps we set to 10 the number of frames to let pass before using worldInfo, should we set our threshold differently? import ARKit import Combine import OSLog import SwiftUI import RealityKit import RealityKitContent let SUBSYSTEM = Bundle.main.bundleIdentifier! struct ImmersiveView: View { let logger = Logger(subsystem: SUBSYSTEM, category: "ImmersiveView") let session = ARKitSession() let worldInfo = WorldTrackingProvider() @State var sceneUpdateSubscription: EventSubscription? = nil @State var deviceTransform: simd_float4x4? = nil @State var numberOfBadWorldInfos = 0 @State var isBadWorldInfoLoged = false var body: some View { RealityView { content in try? await session.run([worldInfo]) sceneUpdateSubscription = content.subscribe(to: SceneEvents.Update.self) { event in guard let pose = worldInfo.queryDeviceAnchor(atTimestamp: CACurrentMediaTime()) else { return } // `worldInfo` does not return correct values for the first few frames (exact number of frames is unknown) // - known SO: https://stackoverflow.com/questions/78396187/how-to-determine-the-first-reliable-position-of-the-apple-vision-pro-device deviceTransform = pose.originFromAnchorTransform if deviceTransform!.columns.3.y < 1.6 { numberOfBadWorldInfos += 1 logger.warning("\(#function) \(#line) deviceTransform.columns.3.y \(deviceTransform!.columns.3.y), numberOfBadWorldInfos \(numberOfBadWorldInfos)") } else { if !isBadWorldInfoLoged { logger.info("\(#function) \(#line) deviceTransform.columns.3.y \(deviceTransform!.columns.3.y), numberOfBadWorldInfos \(numberOfBadWorldInfos)") } isBadWorldInfoLoged = true // stop logging. } } } } }

I am trying to create an object in immersive space that is partially transparent (~50% opacity). I have implemented this in a few different ways including creating a model entity and setting its opacity component to 0.5, and creating a custom material with blending set to a transparent opacity of 0.5. These both work partially, as they behaved as intended for many cases, but seemingly randomly would act like occlusion material and block any other immersive content behind them, showing the real world instead. Some notes: I am using RealityKit to render the semi-transparent object and an opaque object that is behind the semi-transparent object. I am using VisionOS 2.1, and am updating the location of the semi-transparent object often. Both objects are ModelEntities. I would appreciate any guidance on how to implement this. Please let me know if there are any other questions.

My ARViewContainer code is not working. I don't know how to debug the issue and I don't know or see where my results is going to. I need help to resolve this issue. please help debug. See code below:

Hi all, I'm running into an issue with an app that previously worked fine on device using visionOS 2.0. After updating to visionOS 26, the same code runs fine in the simulator but crashes on the device with the following error: -[MTLDebugComputeCommandEncoder _validateThreadsPerThreadgroup:]:1330: failed assertion `(threadsPerThreadgroup.width(32) * threadsPerThreadgroup.height(32) * threadsPerThreadgroup.depth(1))(1024) must be <= 832. (kernel threadgroup size limit)` Is there any documented way to check or increase the allowed threadsPerThreadgroup size on Apple Vision Pro? Or any recommended workaround for this regression? Thanks in advance!

Hello RemoteDeviceIdentifier returns nil and therefore it crashes the HoverEffect sample project. I have vision26 beta 2 on both devices what the correct method of running this code sample ?

Hi, I called it "perspective problem", but I'm not quite sure what it is. I have a tag that I track with builtin camera. I calculate its pose, then use extrinsics and device anchor to calculate where to place entity with model. When I place an entity that overlaps with physical object and start to look at it from different angles, the virtual object begins to move. Initially I thought that it's something wrong with calculations, or some image distortion closer to camera edges is affecting tag detection. To check, I calculated the position only once and displayed entity there, the physical tracked object is not moving. Now, when I move my head, so the object is more to the left, or right in my field of view, the virtual object becomes misaligned to the left, or right. It feels like a parallax effect, but distance from me to entity and to physical object are exactly the same. Is that expected, because of some passthrough correction magic? And if so, can I somehow correct it back, so the entity always overlaps with object? I'm currently on v26 beta 5. I also don't quite understand the camera extrinsics, because it seems that I need to flip it around X by 180 degrees to make it work in deviceAnchor * extrinsics.inverse * tag (shouldn't it be in same coordinates as all other RealityKit things?).

Is there any way to render a RealityView to an Image/UIImage like we used to be able to do using SCNView.snapshot() ? ImageRenderer doesn't work because it renders a SwiftUI view hierarchy, and I need the currently presented RealityView with camera background and 3D scene content the way the user sees it I tried UIHostingController and UIGraphicsImageRenderer like extension View { func snapshot() -> UIImage { let controller = UIHostingController(rootView: self) let view = controller.view let targetSize = controller.view.intrinsicContentSize view?.bounds = CGRect(origin: .zero, size: targetSize) view?.backgroundColor = .clear let renderer = UIGraphicsImageRenderer(size: targetSize) return renderer.image { _ in view?.drawHierarchy(in: view!.bounds, afterScreenUpdates: true) } } } but that leads to the app freezing and sending an infinite loop of [CAMetalLayer nextDrawable] returning nil because allocation failed. Same thing happens when I try return renderer.image { ctx in view.layer.render(in: ctx.cgContext) } Now that SceneKit is deprecated, I didn't want to start a new app using deprecated APIs.

My development team admin requested the Enterprise API for camera access on the vision pro. We got that granted, got a license for usage, and got instructions for integrating it with next steps. We did the following: Even when I try to download and run the sample project for "Accessing the Main Camera", and follow all the exact instructions mentioned here: https://developer.apple.com/documentation/visionos/accessing-the-main-camera I am just unable to receive camera frames. I added the capabilities, created a new provisioning profile with this access, added the entitlements to info.plist and entitlements, replaced the dummy license file with the one we were sent, and also have a matching bundle identifier and development certificate, but it is still not showing camera access for some reason. "Main Camera Access" shows up in our Signing & Capabilities tab, and we also added the NSMainCameraDescription in the Info.plist and allow access while opening the app. None of this works. Not on my app, and not on the sample app that I just downloaded and tried to run on the Vision Pro after replacing the dummy license file.

I am using AccessoryTrackingProvider from ARKit to get the transform of the PSVR2 controller via originFromAnchorTransform of the AccessoryAnchor. I also am trying to use AnchorEntity on the controller using RealityKit However, none of the three options for Accessory.LocationName, which should be used to define the AnchorEntity target, seem to match the position on the controller which is being sent from ARKit. The picture attached is showing two transforms: RealityKit - using .gripSurface to define the AnchoringComponent.Target.accesssory location. ARKit - using originFromAnchorTransform for AccessoryTrackingProvider. They are not aligned at the same point. As for the other options of Accessory.LocationName, using .aim is located at the tip of the controller and .grip is the same position as .gripSurface but with a different orientation. I am wondering why there is not an option for Accessory.LocationName that actually matches the transform captured by ARKit?

Hello Community, I'm encountering an issue with the latest iOS 17 update, specifically related to RoomPlan version-2. In iOS 16, when using RoomPlan version-1, we were able to display stairs in our app. However, after upgrading to iOS 17 and implementing RoomPlan version-2, the stairs are no longer visible. Despite thorough investigation, I couldn't find any option within the code to show or hide stairs, or any other objects for that matter. It seems like a specific issue with the update rather than a coding error on our part. Has anyone else encountered a similar problem? If so, I would greatly appreciate any insights or solutions you might have. It's crucial for our app functionality to have stairs displayed accurately, and we're currently at a loss on how to address this issue. Thank you in advance for any assistance you can provide. Best regards

We are using the ARKit image tracking feature on visionOS 2.0 with three pre-registered images. The image tracking works, but only one image is actively tracked at a time. When more than one target image is visible to the camera, it has difficulty detecting and tracking the other images. Is this the expected behavior in visionOS, or is there something we need to do to resolve this issue?

We're developing a VisionOS application, where we would like to do product recognition (like food items). We have enterprise entitlements and therefore also main camera access for VisionOS. We send this live camera frames to a trained CoreML model where we will receive 2D coordinates from the model detection prediction. Now, we would like to create a 3D anchor on the detected items so it can be visible for user. The 3D anchor is going to be the class name of the detected item. How do we transform this 2D coordinate from the model prediction to a 3D anchor?

Still don't understand why no one is clarifying about this Apple Video https://developer.apple.com/videos/play/wwdc2023/10111 At the end of this video, there's an incomplete tutorial about connecting a USDZ with mesh and Skeleton structure to the hand tracking system. No example project is linked, and no one is giving the community any clarification. Please can you help us to understand how to proceed?

I'm a novice in RealityKit and ARKit. I'm using ARKit in SwiftUI to show a cube with a number as shown below. import SwiftUI import RealityKit import ARKit struct ContentView : View { var body: some View { return ARViewContainer() } } #Preview { ContentView() } struct ARViewContainer: UIViewRepresentable { typealias UIViewType = ARView func makeUIView(context: UIViewRepresentableContext<ARViewContainer>) -> ARView { let arView = ARView(frame: .zero, cameraMode: .ar, automaticallyConfigureSession: true) arView.enableTapGesture() return arView } func updateUIView(_ uiView: ARView, context: UIViewRepresentableContext<ARViewContainer>) { } } extension ARView { func enableTapGesture() { let tapGestureRecognizer = UITapGestureRecognizer(target: self, action: #selector(handleTap(recognizer:))) self.addGestureRecognizer(tapGestureRecognizer) } @objc func handleTap(recognizer: UITapGestureRecognizer) { let tapLocation = recognizer.location(in: self) // print("Tap location: \(tapLocation)") guard let rayResult = self.ray(through: tapLocation) else { return } let results = self.raycast(from: tapLocation, allowing: .estimatedPlane, alignment: .any) if let firstResult = results.first { let position = simd_make_float3(firstResult.worldTransform.columns.3) placeObject(at: position) } } func placeObject(at position: SIMD3<Float>) { let mesh = MeshResource.generateBox(size: 0.3) let material = SimpleMaterial(color: UIColor.systemRed, roughness: 0.3, isMetallic: true) let modelEntity = ModelEntity(mesh: mesh, materials: [material]) var unlitMaterial = UnlitMaterial() if let textureResource = generateTextResource(text: "1", textColor: UIColor.white) { unlitMaterial.color = .init(tint: .white, texture: .init(textureResource)) modelEntity.model?.materials = [unlitMaterial] let id = UUID().uuidString modelEntity.name = id modelEntity.transform.scale = [0.3, 0.1, 0.3] modelEntity.generateCollisionShapes(recursive: true) let anchorEntity = AnchorEntity(world: position) anchorEntity.addChild(modelEntity) self.scene.addAnchor(anchorEntity) } } func generateTextResource(text: String, textColor: UIColor) -> TextureResource? { if let image = text.image(withAttributes: [NSAttributedString.Key.foregroundColor: textColor], size: CGSize(width: 18, height: 18)), let cgImage = image.cgImage { let textureResource = try? TextureResource(image: cgImage, options: TextureResource.CreateOptions.init(semantic: nil)) return textureResource } return nil } } I tap the floor and get a cube with '1' as shown below. The background color of the cube is black, I guess. Where does this color come from and how can I change it into, say, red? Thanks.

Since updating to iOS 26.0 (and confirmed on 26.1), ARBodyTrackingConfiguration no longer detects a valid ARBodyAnchor on devices with LiDAR (e.g., iPhone 15 Pro, iPhone 17 Pro Max). This issue reproduces in custom projects and Apple’s official sample “Capturing Body Motion in 3D”. The AR session runs normally, but the delegate call: func session(_ session: ARSession, didUpdate anchors: [ARAnchor]) never yields an ARBodyAnchor with valid joint transforms. All joints return nil when calling: body.skeleton.modelTransform(for: jointName) resulting in 0 valid joints per frame. Environment • Device: iPhone 17 Pro Max (LiDAR) • iOS: 26.0 / 26.1 • Xcode: 16.0 (stable) • Framework: ARKit + RealityKit • Configuration used: config.worldAlignment = .gravityAndHeading config.isAutoFocusEnabled = true config.environmentTexturing = .none session.run(config) Also tested: with and without frameSemantics = .bodyDetection Expected Behavior ARBodyAnchor should be detected and body.skeleton should contain ~89 valid joints with continuous updates.

I downloaded the official sample project “Accessing the Main Camera”, but I found that it’s not able to retrieve the camera feed on visionOS 26.1. After checking the debug logs, it seems the issue is caused by the system being unable to find the expected format. I tested on a device running visionOS 2, and the camera feed worked correctly — but only when using the sample code from the visionOS 2 version, not the current one. I also noticed that some of the APIs have changed between versions. Has anyone managed to successfully access the camera feed on visionOS 26.1?

What is the reason the hand-tracking joints have these axes? I'm trying to create a virtual hands model and that's a mess.