I am a developer working on developing a space journal application. During the development process, I encountered several crucial strategic and technical decisions, and I would like to hear the experiences of those who have gone through similar situations. Here are the simplified versions of several questions I have. Resource allocation: Which problem should I address first? Design direction: In terms of interaction and UI design, how should I balance "immersion" and "usability"? Market selection: Was it easier for a business to survive in the early stages as a B2B or B2C entity? Cost estimation: How can I reasonably present to my investors the development costs of this project? In order to avoid relying solely on intuition in my decisions, I created a short questionnaire, hoping to gather more structured opinions from my colleagues. If you are also exploring VisionOS, I sincerely hope you can take a few minutes to fill it out. The results are extremely important to me, and I would be more than happy to share the final summary findings with you.

Hello All, I’m working on a computer-vision–heavy iOS application that uses the camera, LiDAR depth maps, and semantic segmentation to reason about the environment (object identification, localization and measurement - not just visualization). Current architecture I initially built the image pipeline around CIImage as a unifying abstraction. It seemed like a good idea because: CIImage integrates cleanly with Vision, ARKit, AVFoundation, Metal, Core Graphics, etc. It provides a rich set of out-of-the-box transforms and filters. It is immutable and thread-safe, which significantly simplified concurrency in a multi-queue pipeline. The LiDAR depth maps, semantic segmentation masks, etc. were treated as CIImages, with conversion to CVPixelBuffer or MTLTexture only at the edges when required. Problem I’ve run into cases where Core Image transformations do not preserve numeric fidelity for non-visual data. Example: Rendering a CIImage-backed segmentation mask into a larger CVPixelBuffer can cause label values to change in predictable but incorrect ways. This occurs even when: using nearest-neighbor sampling disabling color management (workingColorSpace / outputColorSpace = NSNull) applying identity or simple affine transforms I’ve confirmed via controlled tests that: Metal → CVPixelBuffer paths preserve values correctly CIImage → CVPixelBuffer paths can introduce value changes when resampling or expanding the render target This makes CIImage unsafe as a source of numeric truth for segmentation masks and depth-based logic, even though it works well for visualization, and I should have realized this much sooner. Direction I’m considering I’m now considering refactoring toward more intent-based abstractions instead of a single image type, for example: Visual images: CIImage (camera frames, overlays, debugging, UI) Scalar fields: depth / confidence maps backed by CVPixelBuffer + Metal Label maps: segmentation masks backed by integer-preserving buffers (no interpolation, no transforms) In this model, CIImage would still be used extensively — but primarily for visualization and perceptual processing, not as the container for numerically sensitive data. Thread safety concern One of the original advantages of CIImage was that it is thread-safe by design, and that was my biggest incentive. For CVPixelBuffer / MTLTexture–backed data, I’m considering enforcing thread safety explicitly via: Swift Concurrency (actor-owned data, explicit ownership) Questions For those may have experience with CV / AR / imaging-heavy iOS apps, I was hoping to know the following: Is this separation of image intent (visual vs numeric vs categorical) a reasonable architectural direction? Do you generally keep CIImage at the heart of your pipeline, or push it to the edges (visualization only)? How do you manage thread safety and ownership when working heavily with CVPixelBuffer and Metal? Using actor-based abstractions, GCD, or adhoc? Are there any best practices or gotchas around using Core Image with depth maps or segmentation masks that I should be aware of? I’d really appreciate any guidance or experience-based advice. I suspect I’ve hit a boundary of Core Image’s design, and I’m trying to refactor in a way that doesn't involve too much immediate tech debt, remains robust and maintainable long-term. Thank you in advance!

It is vital for Apple to refine its OCR models to correctly distinguish between Khmer and Thai scripts. Incorrectly labeling Khmer text as Thai is more than a technical bug; it is a culturally insensitive error that impacts national identity, especially given the current geopolitical climate between Cambodia and Thailand. Implementing a more robust language-detection threshold would prevent these harmful misidentifications. There is a significant logic flaw in the VNRecognizeTextRequest language detection when processing Khmer script. When the property automaticallyDetectsLanguage is set to true, the Vision framework frequently misidentifies Khmer characters as Thai. While both scripts share historical roots, they are distinct languages with different alphabets. Currently, the model’s confidence threshold for distinguishing between these two scripts is too low, leading to incorrect OCR output in both developer-facing APIs and Apple’s native ecosystem (Preview, Live Text, and Photos). import SwiftUI import Vision class TextExtractor { func extractText(from data: Data, completion: @escaping (String) -> Void) { let request = VNRecognizeTextRequest { (request, error) in guard let observations = request.results as? [VNRecognizedTextObservation] else { completion("No text found.") return } let recognizedStrings = observations.compactMap { observation in let str = observation.topCandidates(1).first?.string return "{text: \(str!), confidence: \(observation.confidence)}" } completion(recognizedStrings.joined(separator: "\n")) } request.automaticallyDetectsLanguage = true // <-- This is the issue. request.recognitionLevel = .accurate let handler = VNImageRequestHandler(data: data, options: [:]) DispatchQueue.global(qos: .background).async { do { try handler.perform([request]) } catch { completion("Failed to perform OCR: \(error.localizedDescription)") } } } } Recognizing Khmer Confidence Score is low for Khmer text. (The output is in Thai language with low confidence score) Recognizing English Confidence Score is high expected. Recognizing Thai Confidence Score is high as expected Issues on Preview, Photos Khmer text Copied text Kouk Pring Chroum Temple [19121 รอาสายสุกตีนานยารรีสใหิสรราภูชิตีนนสุฐตีย์ [รุก เผือชิษาธอยกัตธ์ตายตราพาษชาณา ถวเชยาใบสราเบรถทีมูสินตราพาษชาณา ทีมูโษา เช็ก อาษเชิษฐอารายสุกบดตพรธุรฯ ตากร"สุก"ผาตากรธกรธุกเยากสเผาพศฐตาสาย รัอรณาษ"ตีพย" สเผาพกรกฐาภูชิสาเครๆผู:สุกรตีพาสเผาพสรอสายใผิตรรารตีพสๆ เดียอลายสุกตีน ธาราชรติ ธิพรหณาะพูชุบละเาหLunet De Lajonquiere ผารูกรสาราพารผรผาสิตภพ ตารสิทูก ธิพิ คุณที่นสายเระพบพเคเผาหนารเกะทรนภาษเราภุพเสารเราษทีเลิกสญาเราหรุฬารชสเกาก เรากุม สงสอบานตรเราะากกต่ายภากายระตารุกเตียน Recommended Solutions 1. Set a Threshold Filter out the detected result where the threshold is less than or equal to 0.5, so that it would not output low quality text which can lead to the issue. For example, let recognizedStrings = observations.compactMap { observation in if observation.confidence <= 0.5 { return nil } let str = observation.topCandidates(1).first?.string return "{text: \(str!), confidence: \(observation.confidence)}" } 2. Add Khmer Language Support This issue would never happen if the model has the capability to detect and recognize image with Khmer language. Doc2Text GitHub: https://github.com/seanghay/Doc2Text-Swift

Hello everyone, I am currently developing an app for my Swift Student Challenge submission that focuses on human motion analysis using the Vision framework. To effectively demonstrate the app's technical capabilities during the review process, I need to include a sample video showing a person performing specific movements. However, I want to ensure that my submission strictly adheres to all intellectual property guidelines. Instead of using existing copyrighted videos or public social media clips, I am considering using Generative AI to create an original, royalty-free sample video. This video would feature a character performing movements designed specifically to test my app's pose estimation and feedback logic. I have a few questions regarding this approach: Is it acceptable to use AI-generated sample assets (like video clips) to demonstrate technical features when it's difficult to record high-quality personal footage due to environmental constraints? If I clearly disclose the tools used and the reason for using AI-generated content in my written response, would this be considered a professional approach to asset management? Are there any specific guidelines I should follow to ensure that the use of AI-generated samples doesn't overshadow the original coding and design work of the project? My goal is to showcase a polished and technically sound implementation using Xcode 26 while respecting all copyright requirements. Thank you for your time and advice!

Hi, I am modifying the sample camera app that is here: https://developer.apple.com/tutorials/sample-apps/capturingphotos-camerapreview ... In the processPreviewImages, I am using the Vision APIs to generate a segmentation mask for a person/object, then compositing that person onto a different background (with some other filtering). The filtering and compositing is done via CoreImage. At the end, I convert the CIImage to a CGImage then to a SwiftUI Image. When I run it on my iPhone, it works fine, and has not crashed. When I run it on the iPhone with the debugger, it crashes within a few seconds with: EXC_BAD_ACCESS in libRPAC.dylib`std::__1::__hash_table<std::__1::__hash_value_type<long, qos_info_t>, std::__1::__unordered_map_hasher<long, std::__1::__hash_value_type<long, qos_info_t>, std::__1::hash, std::__1::equal_to, true>, std::__1::__unordered_map_equal<long, std::__1::__hash_value_type<long, qos_info_t>, std::__1::equal_to, std::__1::hash, true>, std::__1::allocator<std::__1::__hash_value_type<long, qos_info_t>>>::__emplace_unique_key_args<long, std::__1::piecewise_construct_t const&, std::__1::tuple<long const&>, std::__1::tuple<>>: It had previously been working fine with the debugger, so I'm not sure what has changed. Is there a difference in how the Vision APIs are executed if the debugger is attached vs. not?

I'm trying the new RecognizeDocumentsRequest supposed to detect paragraphs (among other things) in a document. I tried many source images, and I don't see the slightest difference compared to the old API (VN)RecognizedTextRequest Is it supposed to not work or is it in beta?

直播过程中需同时操作 Vision Pro（拍摄）、Mac（推流）、中控台（画面切换），无统一控制入口，调节 3D 模型、校准画质等操作需在多设备间切换，易出错且效率低。 期望 针对直播场景，提供桌面端专属控制软件，支持一站式管理 Vision Pro 的拍摄参数、3D 模型切换、虚实融合效果等，实现多设备协同操作的可视化、便捷化。

画面亮度存在无规律动态波动（时亮时暗），且无手动控制入口，导致商品颜色还原失真、主播面部曝光异常（过曝 / 欠曝），严重影响直播展示效果。 期望 "· 优化直播模式的自动曝光算法，提升复杂光线环境下的亮度稳定性； · 增加 “直播模式” 专属亮度锁定功能，支持手动设定亮度参数并锁定，满足直播场景下的画质可控需求。 "

切换后两者的亮度、色彩饱和度、对比度等画质参数差距较大，导致画面视觉体验割裂，破坏直播连贯性，影响用户观看沉浸感。 期望 "· 对标常规直播单反相机的画质基准，优化 Vision Pro 的画面亮度、色彩还原能力； · 提供设备端或配套软件的画质自定义调节功能（亮度、对比度、色温等），支持直播前手动校准，确保与单反相机画面风格一致。"

传输后的直播流分辨率显著下降，画面细节丢失、清晰度不足，导致 3D 家具商品的纹理、尺寸等关键信息无法精准展示，影响用户对商品的判断。 期望 优化流传输过程中的分辨率压缩策略，减少传输过程中的画质损耗，提升 Mac 端接收的直播流清晰度，匹配 3D 商品展示的高精度需求。

佩戴者头部自然晃动时，设备拍摄的画面会出现明显抖动，导致观看直播的用户产生眩晕感，严重影响直播沉浸体验和购物决策效率。 希望 优化设备内置防抖算法，降低头部常规晃动对画面稳定性的影响，提升直播画面的流畅度。

I'm receiving output from avcapturesession and capturing an image using Vision, but the image is output in landscape orientation instead of portrait. Even when I set the orientation to up in ciimage, cgimage, and uiimage, the image is still output in landscape orientation. On iPhones 16 and below, the image is output in portrait orientation. But on iPhones 17 and above, the image is output in landscape orientation. Please help.

I'm using Vision framework (DetectFaceLandmarksRequest) with the same code and the same test image to detect face landmarks. On iOS 18 everything works as expected: detected face landmarks align with the face correctly. But when I run the same code on devices with iOS 26, the landmark coordinates are outside the [0,1] range, which indicates they are out of face bounds. Fun fact: the old VNDetectFaceLandmarksRequest API works very well without encountering this issue How I get face landmarks: private let faceRectangleRequest = DetectFaceRectanglesRequest(.revision3) private var faceLandmarksRequest = DetectFaceLandmarksRequest(.revision3) func detectFaces(in ciImage: CIImage) async throws -> FaceTrackingResult { let faces = try await faceRectangleRequest.perform(on: ciImage) faceLandmarksRequest.inputFaceObservations = faces let landmarksResults = try await faceLandmarksRequest.perform(on: ciImage) ... } How I show face landmarks in SwiftUI View: private func convert( point: NormalizedPoint, faceBoundingBox: NormalizedRect, imageSize: CGSize ) -> CGPoint { let point = point.toImageCoordinates( from: faceBoundingBox, imageSize: imageSize, origin: .upperLeft ) return point } At the same time, it works as expected and gives me the correct results: region is FaceObservation.Landmarks2D.Region let points: [CGPoint] = region.pointsInImageCoordinates( imageSize, origin: .upperLeft ) After that, I found that the landmarks are normalized relative to the unalignedBoundingBox. However, I can’t access it in code. Still, using these values for the bounding box works correctly. Things I've already tried: Same image input Tested multiple devices on iOS 26.2 -> always wrong. Tested multiple devices on iOS 18.7.1 -> always correct. Environment: macOS 26.2 Xcode 26.2 (17C52) Real devices, not simulator Face Landmarks iOS 18 Face Landmarks iOS 26

I am new to Swift and iOS development, and I have a question about video capture performance. Is it possible to capture video at a resolution of 4032×3024 while simultaneously running a vision/ML model on the video stream (e.g., using Vision or CoreML)? I want to know: whether iOS devices support capturing video at that resolution, whether the frame rate drops significantly at that scale, and whether it is practical to run a Vision/ML model in real-time while recording at such a high resolution. If anyone has experience with high-resolution AVCaptureSession setups or combining them with real-time ML processing, I would really appreciate guidance or sample code.

Hi everyone, I’ve been analyzing the current state of Sign Language accessibility tools, and I noticed a significant gap in learning tools: we lack real-time feedback for students (e.g., "Is my hand position correct?"). Most current solutions rely on 2D video processing, which struggles with depth perception and occlusion (hand-over-hand or hand-over-face gestures), which are critical in Sign Language grammar. I'd like to propose/discuss an architecture leveraging the current LiDAR + Neural Engine capabilities found in iPhone devices to solve this. The Concept: Skeleton-based Normalization Instead of training ML models on raw video frames (which introduces noise from lighting, skin tone, and clothing), we could use ARKit's Body Tracking to abstract the input. Capture: Use ARKit/LiDAR to track the user's upper body and hand joints in 3D space. Data Normalization: Extract only the vector coordinates (X, Y, Z of joints). This creates a "clean" dataset, effectively normalizing the user regardless of physical appearance. Comparison: Feed these vectors into a CoreML model trained on "Reference Skeletons" (recorded by native signers). Feedback Loop: The app calculates the geometric distance between the user's pose and the reference pose to provide specific correction (e.g., "Raise your elbow 10 degrees"). Why this approach? Solves Occlusion: LiDAR handles depth much better than standard RGB cameras when hands cross the body. Privacy: We are processing coordinates, not video streams. Efficiency: Comparing vector sequences is computationally cheaper than video analysis, preserving battery life. Has anyone experimented with using ARKit Body Anchors specifically for comparing complex gesture sequences against a stored "correct" database? I believe this "Skeleton First" approach is the key to scalable Sign Language education apps. Looking forward to hearing your thoughts.

Is foundation models matured enough to take input from the Apple Vision framework to generate responses? Something similar to what google's gemini does although in a much smaller scale and for a very specific niche.

I'm on Tahoe 26.1 / M3 Macbook Air. I'm using VNDetectFaceRectanglesRequest as properly as possible, as in the minimal command line program attached below. For some reason, I always get: MLE5Engine is disabled through the configuration printed. I couldn't find any notes on developer docs saying that VNDetectFaceRectanglesRequest can not use the Apple Neural Engine. I'm assuming there is something wrong with my code however I wasn't able to find any remarks from documentation where it might be. I wasn't able to find the above error message online either. I would appreciate your help a lot and thank you in advance. The code below accesses the video from AVCaptureDevice.DeviceType.builtInWideAngleCamera. Currently it directly chooses the 0th format which has the largest resolution (Full HD on my M3 MBA) and "4:2:0" color "v" reduced color component spectrum encoding ("420v"). After accessing video, it performs a VNDetectFaceRectanglesRequest. It prints "VNDetectFaceRectanglesRequest completion Handler called" many times, then prints the error message above, then continues printing "VNDetectFaceRectanglesRequest completion Handler called" until the user quits it. To run it in Xcode, File > New project > Mac command line tool. Pasting the code below, then click on the root file > Targets > Signing & Capabilities > Hardened Runtime > Resource Access > Camera. A possible explanation could be that either Apple's internal CoreML code for this function works on GPU/CPU only or it doesn't accept 420v as supplied by the Macbook Air camera import AVKit import Vision var videoDataOutput: AVCaptureVideoDataOutput = AVCaptureVideoDataOutput() var detectionRequests: [VNDetectFaceRectanglesRequest]? var videoDataOutputQueue: DispatchQueue = DispatchQueue(label: "queue") class XYZ: /*NSViewController or NSObject*/NSObject, AVCaptureVideoDataOutputSampleBufferDelegate { func viewDidLoad() { //super.viewDidLoad() let session = AVCaptureSession() let inputDevice = try! self.configureFrontCamera(for: session) self.configureVideoDataOutput(for: inputDevice.device, resolution: inputDevice.resolution, captureSession: session) self.prepareVisionRequest() session.startRunning() } fileprivate func highestResolution420Format(for device: AVCaptureDevice) -> (format: AVCaptureDevice.Format, resolution: CGSize)? { let deviceFormat = device.formats[0] print(deviceFormat) let dims = CMVideoFormatDescriptionGetDimensions(deviceFormat.formatDescription) let resolution = CGSize(width: CGFloat(dims.width), height: CGFloat(dims.height)) return (deviceFormat, resolution) } fileprivate func configureFrontCamera(for captureSession: AVCaptureSession) throws -> (device: AVCaptureDevice, resolution: CGSize) { let deviceDiscoverySession = AVCaptureDevice.DiscoverySession(deviceTypes: [AVCaptureDevice.DeviceType.builtInWideAngleCamera], mediaType: .video, position: AVCaptureDevice.Position.unspecified) let device = deviceDiscoverySession.devices.first! let deviceInput = try! AVCaptureDeviceInput(device: device) captureSession.addInput(deviceInput) let highestResolution = self.highestResolution420Format(for: device)! try! device.lockForConfiguration() device.activeFormat = highestResolution.format device.unlockForConfiguration() return (device, highestResolution.resolution) } fileprivate func configureVideoDataOutput(for inputDevice: AVCaptureDevice, resolution: CGSize, captureSession: AVCaptureSession) { videoDataOutput.setSampleBufferDelegate(self, queue: videoDataOutputQueue) captureSession.addOutput(videoDataOutput) } fileprivate func prepareVisionRequest() { let faceDetectionRequest: VNDetectFaceRectanglesRequest = VNDetectFaceRectanglesRequest(completionHandler: { (request, error) in print("VNDetectFaceRectanglesRequest completion Handler called") }) // Start with detection detectionRequests = [faceDetectionRequest] } // MARK: AVCaptureVideoDataOutputSampleBufferDelegate // Handle delegate method callback on receiving a sample buffer. public func captureOutput(_ output: AVCaptureOutput, didOutput sampleBuffer: CMSampleBuffer, from connection: AVCaptureConnection) { var requestHandlerOptions: [VNImageOption: AnyObject] = [:] let cameraIntrinsicData = CMGetAttachment(sampleBuffer, key: kCMSampleBufferAttachmentKey_CameraIntrinsicMatrix, attachmentModeOut: nil) if cameraIntrinsicData != nil { requestHandlerOptions[VNImageOption.cameraIntrinsics] = cameraIntrinsicData } let pixelBuffer = CMSampleBufferGetImageBuffer(sampleBuffer)! // No tracking object detected, so perform initial detection let imageRequestHandler = VNImageRequestHandler(cvPixelBuffer: pixelBuffer, orientation: CGImagePropertyOrientation.up, options: requestHandlerOptions) try! imageRequestHandler.perform(detectionRequests!) } } let X = XYZ() X.viewDidLoad() sleep(9999999)

On iOS 26.1, this throws on the 2020 iPad Pro (4th gen) but works fine on an M4 iPad Pro or iPhone 15 Pro: guard let device = AVCaptureDevice.default(.builtInLiDARDepthCamera, for: .video, position: .back) else { throw ConfigurationError.lidarDeviceUnavailable } It's just the standard code from Apple's own sample code so obviously used to work: https://developer.apple.com/documentation/AVFoundation/capturing-depth-using-the-lidar-camera Does it fail because Apple have silently dumped support for the older LiDAR sensor used prior to the M4 iPad Pro, or is there another reason? What about the 5th and 6th gen iPad Pro, does it still work on those?

Hi all! Nice to meet you., I am planning to build an iOS application that can: Capture an image using the camera or select one from the gallery. Remove the background and keep only the detected main object. Add a border (outline) around the detected object’s shape. Apply an animation along that border (e.g., moving light or glowing effect). Include a transition animation when removing the background — for example, breaking the background into pieces as it disappears. The app Capword has a similar feature for object isolation, and I’d like to build something like that. Could you please provide any guidance, frameworks, or sample code related to: Object segmentation and background removal in Swift (Vision or Core ML). Applying custom borders and shape animations around detected objects. Recognizing the object name (e.g., “person”, “cat”, “car”) after segmentation. Thank you very much for your support. Best regards, SINN SOKLYHOR

Hi, I'm trying to use the new RecognizeDocumentsRequest from the Vision Framework to read a receipt. It looks very promising by being able to read paragraphs, lines and detect data. So far it unfortunately seems to read every line on the receipt as a paragraph and when there is more space on one line it creates two paragraphs. Is there perhaps an Apple Engineer who knows if this is expected behaviour or if I should file a Feedback for this? Code setup: let request = RecognizeDocumentsRequest() let observations = try await request.perform(on: image) guard let document = observations.first?.document else { return } for paragraph in document.paragraphs { print(paragraph.transcript) for data in paragraph.detectedData { switch data.match.details { case .phoneNumber(let data): print("Phone: \(data)") case .postalAddress(let data): print("Postal: \(data)") case .calendarEvent(let data): print("Calendar: \(data)") case .moneyAmount(let data): print("Money: \(data)") case .measurement(let data): print("Measurement: \(data)") default: continue } } } See attached image as an example of a receipt I'd like to parse. The top 3 lines are the name, street, and postal code + city. These are all separate paragraphs. Checking on detectedData does see the street (2nd line) as PostalAddress, but not the complete address. Might that be a location thing since it's a Dutch address. And lower on the receipt it sees the block with "Pomp 1 95 Ongelood" and the things below also as separate paragraphs. First picking up the left side and after that the right side. So it's something like this: * Pomp 1 Volume Prijs € TOTAAL * BTW Netto 21.00 % 95 Ongelood 41,90 l 1.949/ 1 81.66 € 14.17 67.49