Hello, ARKit already have ways to identify walls, doors, chairs and other objects: ARMeshClassification ARPlaneAnchor.Classification Here there seems to say that RoomPlan is powered by a distinct (although similar) algorithms and AI model than ARKit scene understanding. Is it correct? I was wondering what was exactly the point of designing a new algorithm from scratch and also which of them present better performance and more reliable results? Why are two different methods designed for the same purpose integrated in the framework?

I would like to do object detection that can not be done with RoomPlan. I'm trying to do 3D object detection using point clouds. Can I scan a room with RoomPlan and do my own object detection at the same time? Also, is it possible to additionally display the bounding box of the recognized object? What kind of object detection method is Apple currently using in RoomPlan? Best regards,

大家好，请教一下，oc与swift混编，swift写的roomplan代码与官方提供的代码一样，但是roomplan的roomCaptureView的代理方法不走，我检查了代码，也打了断点，看了delegate是有值的，不知道有没有大佬帮我解决一下这个问题，我将表示感谢！

Hello, I would like to be able to modify/manage my own instance of the structure CapturedRoom in RoomPlan, and still be able to export it to usdz. Any idea how this can be done? Same question for CaputredRoom.Surface. Thanks!

I use RoomPlan to scan and get 3d room visualization. When I get the scan result, the floor appears. When I export this result to USDZ, I get walls in USDZ files but not the floor . Does it an bug of RoomPlan export method or it's normal and I have to activate/desactivate parameters to get the floor in my USDZ file ? I searched in documentation, I have not found anythings about that. Thanks for your help

I can not find any documentation on how to interpret and use the data in the returned scan data objects. Specifically, in the captured room wall surfaces.

Hi, I am trying to create a 2D floor plan from the 3D model that RoomPlan creates. This was a FAQ in the augmented-reality Apple Slack channel and the answer given was "RoomPlan outputs a 3D floor plan. You may set the z-coordinate to 0, which will flatten it and thus give you a 2D top-down floor plan." Does anyone know what this z-coordinate is and how to change it? Thank you

Hello, are there are any parameters in the RoomPlan source code or Data API that can be fine tuned, so that walls and windows may be identified easier?

Does anyone know if there's a native library or API to align two point clouds in Swift/ARKit such as ICP? I know it's possible to do it in Python using the Open3D library http://www.open3d.org/docs/release/tutorial/pipelines/icp_registration.html It seems like ARWorldMap would need some sort of similar capability to do tracking and resume the session from the same state later., so I'm curious if anyone knows how it works under the hood. Or if you have any suggestions, I'd appreciate some pointers. Thank you.

Hi community,We have some of the generated usdz files need to be convert to CapturedRoom object or JSON format. But we haven't found the relevant method.Can you tell me how to do this

The position of the wall is represented by transform: simd_float4x4, how a know start point and end point of wall

Hello, In RoomPlan, all the functions captureSession() use a CapturedRoom as parameter except when we complete a session where raw data( CapturedRoomData) is passed as parameter (RoomCaptureSessionDelegate documentation) My question is: Why is that? What can be done with the raw data apart from converting it to a CapturedRoom? Why aren't we directly provided with a CapturedRoom instead of raw data at this point? Why do we receive a CapturedRoomData at the end of the session but a CapturedRoom during the scan? func captureSession(RoomCaptureSession, didUpdatewith: CapturedRoom) func captureSession(RoomCaptureSession, didEndWith: CapturedRoomData) // RAW DATA I am thinking that maybe I missed some important point. Thanks!

We have capturedRoom data with the help of RoomPlan API. When we are exporting this data with the help of export function but we are getting "EXC_BAD_ACCESS (code=1, address=0x0)" Please help us. https://developer.apple.com/documentation/roomplan/capturedroom#generating-a-usdz-file let url = FileManager.default.temporaryDirectory.appending(path: "Room.usdz") try capturedRoom.export(to: url, exportOptions: .parametric)

There are some old answers out there... but is there ARKit, RealityKit, and RoomPlan way to do this? Thanks in advance.

RoomCaptureView can export data to USDZ file, but i need file output is gltF, any sulution,

Apple's RoomPlan demo software page says it is powered by RealityKit, but I am having troubles finding any hooks into the standard RealityKit APIs. For example, RoomPlanView doesn't seem to be related to ARView, and I cannot find any Scene property to access (or add) RealityKit entities. Does anyone know if these RealityKit classes are accessible through RoomPlanView? Note: I did find the ARSession through roomCaptureView?.captureSession.arSession

I'm sharing this in case someone else wants to use Apple's RoomPlan to create a model and import it into Blender. The problem: I could not successfully import a USDZ model from the RoomPlan app into Blender. (I went through the normal process of importing a USDZ file into Blender: change the file type from ".usdz" to ".zip"; unzipped the file; then tried to import the ".usda" file). No surfaces appeared. The solution: In Apple's source code from here, in the file RoomCaptureViewController.swift, I changed the line try finalResults?.export(to: destinationURL, exportOptions: .parametric) to try finalResults?.export(to: destinationURL, exportOptions: .mesh) recompiled, and went through the USDZ to USDA conversion process again. This time it worked. Apparently Blender cannot import parametric USDA models.

Our office room has a round cylindrical corner. But the current RoomPlan example App represents the curved corner by using edges (straight lines): CapturedRoom.Surface.Edge. We are looking for representing the round corner by using curves: CapturedRoom.Surface.Curve. The source code of an ARKit App of us using depthMap is public on GitHub CurvSurf. We are looking for an in-depth help from you.

I am getting data with CapturedRoom Surface but only with the specified Codable struct provided by Apple's framework. I need to export more data from this. I'm getting the data in the Log but as a Codable struct.

Hi, I want to extract real textures of the objects detected by RoomPlanAPI. So, that i can apply them later on to the model generated by RoomPlan. I want to create an illusion of the real room so that i can have the control over the objects. Does anyone have any idea how can i do that?