mrousavy · mrousavy · Jun 22, 2026
diff --git a/docs/content/docs/a-depth-frame.mdx b/docs/content/docs/a-depth-frame.mdx
@@ -59,12 +59,13 @@ const buffer = depth.getDepthData()
 
 #### Interpreting Depth Data
 
-The Depth Data's layout depends on the [`Depth`](/api/react-native-vision-camera/hybrid-objects/Depth)'s [`pixelFormat`](/api/react-native-vision-camera/hybrid-objects/Depth#pixelformat). For example, in [`'depth-16-bit'`](/api/react-native-vision-camera/type-aliases/DepthPixelFormat), pixels are laid out in 16-bit floats - one float per "pixel".
+The Depth Data's layout depends on the [`Depth`](/api/react-native-vision-camera/hybrid-objects/Depth)'s [`pixelFormat`](/api/react-native-vision-camera/hybrid-objects/Depth#pixelformat). On iOS, [`'depth-16-bit'`](/api/react-native-vision-camera/type-aliases/DepthPixelFormat) stores one 16-bit float depth sample per pixel. On Android, [`'depth-16-bit'`](/api/react-native-vision-camera/type-aliases/DepthPixelFormat) maps to `ImageFormat.DEPTH16`, where each 16-bit sample stores range and confidence bits.
 
 ```ts
 const depth = ...
 const buffer = depth.getDepthData()
-if (depth.pixelFormat === 'depth-16') {
+if (depth.pixelFormat === 'depth-16-bit') {
+  // iOS depth-16-bit data is Float16. Android DEPTH16 uses packed Uint16 samples.
   const pixels = new Float16Array(buffer)
   // [!code ++]
   const distanceToFirstPixel = pixels[0]
@@ -73,7 +74,8 @@ if (depth.pixelFormat === 'depth-16') {
 ```
 
 > [!TIP]
-> Typically, a single 16-bit float in [`'depth-16-bit'`](/api/react-native-vision-camera/type-aliases/DepthPixelFormat) data represents a distance in meters.
+> On iOS, a single 16-bit float in [`'depth-16-bit'`](/api/react-native-vision-camera/type-aliases/DepthPixelFormat) data represents a distance in meters.
+> On Android, read `ImageFormat.DEPTH16` as unsigned 16-bit samples: the low 13 bits are range in millimeters and the high 3 bits are confidence.
 
 #### Converting between Depth Formats
 

diff --git a/docs/content/docs/a-frame.mdx b/docs/content/docs/a-frame.mdx
@@ -75,7 +75,7 @@ console.log(frame.pixelFormat) // 'yuv-420-8-bit-full'
 ```
 
 While the most commonly known [`PixelFormat`](/api/react-native-vision-camera/type-aliases/PixelFormat) is RGB (often [`'rgb-bgra-8-bit'`](/api/react-native-vision-camera/type-aliases/VideoPixelFormat)), it is not natively produced by the Camera, which means it requires expensive conversion causing higher latency, more bandwidth, and overall slower performance.
-The Camera's native pixel format is typically YUV (often [`'yuv-420-8-bit-full'`](/api/react-native-vision-camera/type-aliases/VideoPixelFormat)) or a vendor-specific variation of it ([`'private'`](/api/react-native-vision-camera/type-aliases/PixelFormat)), which uses ~50% less memory than RGB and requires little to no conversion overhead.
+The Camera's native pixel format is typically YUV (for example [`'yuv-420-8-bit-video'`](/api/react-native-vision-camera/type-aliases/VideoPixelFormat) on iOS native capture or [`'yuv-420-8-bit-full'`](/api/react-native-vision-camera/type-aliases/VideoPixelFormat) for common CPU-readable YUV paths), or a vendor-specific variation of it ([`'private'`](/api/react-native-vision-camera/type-aliases/PixelFormat)), which uses ~50% less memory than RGB and requires little to no conversion overhead.
 
 > [!NOTE]
 > See ["Frame Output: Choosing a Pixel Format"](frame-output#choosing-a-pixel-format) for more information about configuring the Pixel Format a [`CameraFrameOutput`](/api/react-native-vision-camera/hybrid-objects/CameraFrameOutput) streams in.
@@ -132,7 +132,7 @@ if (frame.isPlanar) {
     const uvBuffer = planes[1].getPixelBuffer()
     const yPixels = new Uint8Array(yBuffer)
     const uvPixels = new Uint8Array(uvBuffer)
-    const firstPixel = { y: yPixels[0], u: uvPixels[0], v: uvPixels[0] }
+    const firstPixel = { y: yPixels[0], u: uvPixels[0], v: uvPixels[1] }
   }
 } else {
   // regular pixel buffer access

diff --git a/docs/content/docs/pixel-formats-map.mdx b/docs/content/docs/pixel-formats-map.mdx
@@ -28,10 +28,13 @@ In a [`CameraFrameOutput`](/api/react-native-vision-camera/hybrid-objects/Camera
 
 When you receive a [`Frame`](/api/react-native-vision-camera/hybrid-objects/Frame), you can inspect its [`pixelFormat`](/api/react-native-vision-camera/hybrid-objects/Frame#pixelformat) to find out the precise Pixel Format it uses - here are some examples that map to native pixel formats:
 
-| VisionCamera [`VideoPixelFormat`](/api/react-native-vision-camera/type-aliases/VideoPixelFormat) | iOS [`CVPixelFormatType`](https://developer.apple.com/documentation/corevideo/cvpixelformattype) | Android [`ImageFormat`](https://developer.android.com/reference/android/graphics/ImageFormat) |
+| VisionCamera [`PixelFormat`](/api/react-native-vision-camera/type-aliases/PixelFormat) | iOS [`CVPixelFormatType`](https://developer.apple.com/documentation/corevideo/cvpixelformattype) | Android format |
 |---------------|--------|---------------------|
+| [`yuv-420-8-bit-video`](/api/react-native-vision-camera/type-aliases/VideoPixelFormat) | [`420YpCbCr8BiPlanarVideoRange`](https://developer.apple.com/documentation/corevideo/kcvpixelformattype_420ypcbcr8biplanarvideorange) | [`YUV_420_888`](https://developer.android.com/reference/android/graphics/ImageFormat#YUV_420_888) + limited-range `DataSpace` |
 | [`yuv-420-8-bit-full`](/api/react-native-vision-camera/type-aliases/VideoPixelFormat) | [`420YpCbCr8BiPlanarFullRange`](https://developer.apple.com/documentation/CoreVideo/kCVPixelFormatType_420YpCbCr8BiPlanarFullRange) | [`YUV_420_888`](https://developer.android.com/reference/android/graphics/ImageFormat#YUV_420_888) |
 | [`yuv-420-10-bit-full`](/api/react-native-vision-camera/type-aliases/VideoPixelFormat) | [`420YpCbCr10BiPlanarFullRange`](https://developer.apple.com/documentation/corevideo/kcvpixelformattype_420ypcbcr10biplanarfullrange) | [`YCBCR_P010`](https://developer.android.com/reference/android/graphics/ImageFormat#YCBCR_P010) |
+| [`yuv-444-10-bit-video`](/api/react-native-vision-camera/type-aliases/VideoPixelFormat) | [`444YpCbCr10BiPlanarVideoRange`](https://developer.apple.com/documentation/corevideo/kcvpixelformattype_444ypcbcr10biplanarvideorange) | / |
+| [`yuv-444-10-bit-full`](/api/react-native-vision-camera/type-aliases/VideoPixelFormat) | [`444YpCbCr10BiPlanarFullRange`](https://developer.apple.com/documentation/corevideo/kcvpixelformattype_444ypcbcr10biplanarfullrange) | / |
 | [`rgb-bgra-8-bit`](/api/react-native-vision-camera/type-aliases/VideoPixelFormat) | [`32BGRA`](https://developer.apple.com/documentation/CoreVideo/kCVPixelFormatType_32BGRA) | / |
-| [`rgb-rgba-8-bit`](/api/react-native-vision-camera/type-aliases/VideoPixelFormat) | / | [`FLEX_RGBA_888`](https://developer.android.com/reference/android/graphics/ImageFormat#FLEX_RGBA_888) |
-| [`private`](/api/react-native-vision-camera/type-aliases/VideoPixelFormat) | / | [`PRIVATE`](https://developer.android.com/reference/android/graphics/ImageFormat#PRIVATE) |
+| [`rgb-rgba-8-bit`](/api/react-native-vision-camera/type-aliases/VideoPixelFormat) | [`32RGBA`](https://developer.apple.com/documentation/corevideo/kcvpixelformattype_32rgba) | [`PixelFormat.RGBA_8888`](https://developer.android.com/reference/android/graphics/PixelFormat#RGBA_8888) or [`FLEX_RGBA_8888`](https://developer.android.com/reference/android/graphics/ImageFormat#FLEX_RGBA_8888) |
+| [`private`](/api/react-native-vision-camera/type-aliases/PixelFormat) | / | [`PRIVATE`](https://developer.android.com/reference/android/graphics/ImageFormat#PRIVATE) |
diff --git a/...c/main/java/com/margelo/nitro/camera/extensions/converters/PixelFormat+fromImageFormat.kt b/...c/main/java/com/margelo/nitro/camera/extensions/converters/PixelFormat+fromImageFormat.kt
@@ -3,6 +3,7 @@ package com.margelo.nitro.camera.extensions.converters
 import android.graphics.ImageFormat
 import com.margelo.nitro.camera.PixelFormat
 import com.margelo.nitro.camera.utils.PixelRange
+import android.graphics.PixelFormat as AndroidPixelFormat
 
 fun PixelFormat.Companion.fromImageFormat(
   imageFormat: Int,
@@ -11,6 +12,8 @@ fun PixelFormat.Companion.fromImageFormat(
   return when (imageFormat) {
     ImageFormat.FLEX_RGB_888 -> PixelFormat.RGB_RGB_8_BIT
     ImageFormat.FLEX_RGBA_8888 -> PixelFormat.RGB_RGBA_8_BIT
+    AndroidPixelFormat.RGB_888 -> PixelFormat.RGB_RGB_8_BIT
+    AndroidPixelFormat.RGBA_8888 -> PixelFormat.RGB_RGBA_8_BIT
     ImageFormat.DEPTH16 -> PixelFormat.DEPTH_16_BIT
     ImageFormat.DEPTH_POINT_CLOUD -> PixelFormat.DEPTH_POINT_CLOUD_32_BIT
     ImageFormat.YUV_420_888 -> {

diff --git a/...ve-vision-camera/android/src/main/java/com/margelo/nitro/camera/utils/ImageFormatUtils.kt b/...ve-vision-camera/android/src/main/java/com/margelo/nitro/camera/utils/ImageFormatUtils.kt
@@ -1,6 +1,7 @@
 package com.margelo.nitro.camera.utils
 
 import android.graphics.ImageFormat
+import android.graphics.PixelFormat as AndroidPixelFormat
 
 object ImageFormatUtils {
   val allVideoFormats =
@@ -15,6 +16,8 @@ object ImageFormatUtils {
       // RGB
       ImageFormat.FLEX_RGB_888,
       ImageFormat.FLEX_RGBA_8888,
+      AndroidPixelFormat.RGB_888,
+      AndroidPixelFormat.RGBA_8888,
     )
   val allDepthFormats =
     arrayOf(

diff --git a/...ct-native-vision-camera/ios/Extensions/AVFoundation/AVCaptureDevice.Format+bitDepth.swift b/...ct-native-vision-camera/ios/Extensions/AVFoundation/AVCaptureDevice.Format+bitDepth.swift
@@ -12,9 +12,11 @@ extension AVCaptureDevice.Format {
   var bitDepth: DynamicRangeBitDepth {
     let pixelFormat = self.formatDescription.mediaSubType
     switch pixelFormat {
-    case .yuv4208BitVideo, .yuv4208BitFull, .yuv4228BitVideo, .yuv4228BitFull:
+    case .yuv4208BitVideo, .yuv4208BitFull, .yuv4228BitVideo, .yuv4228BitFull,
+      .yuv4448BitVideo, .yuv4448BitFull:
       return .sdr8Bit
-    case .yuv42010BitVideo, .yuv42010BitFull, .yuv42210BitVideo, .yuv42210BitFull:
+    case .yuv42010BitVideo, .yuv42010BitFull, .yuv42210BitVideo, .yuv42210BitFull,
+      .yuv44410BitVideo, .yuv44410BitFull:
       return .hdr10Bit
     default:
       return .unknown

diff --git a/...-native-vision-camera/ios/Extensions/AVFoundation/AVCaptureDevice.Format+colorRange.swift b/...-native-vision-camera/ios/Extensions/AVFoundation/AVCaptureDevice.Format+colorRange.swift
@@ -12,9 +12,11 @@ extension AVCaptureDevice.Format {
   var colorRange: ColorRange {
     let pixelFormat = self.formatDescription.mediaSubType
     switch pixelFormat {
-    case .yuv4208BitVideo, .yuv42010BitVideo, .yuv4228BitVideo, .yuv42210BitVideo:
+    case .yuv4208BitVideo, .yuv42010BitVideo, .yuv4228BitVideo, .yuv42210BitVideo,
+      .yuv4448BitVideo, .yuv44410BitVideo:
       return .video
-    case .yuv4208BitFull, .yuv42010BitFull, .yuv4228BitFull, .yuv42210BitFull:
+    case .yuv4208BitFull, .yuv42010BitFull, .yuv4228BitFull, .yuv42210BitFull,
+      .yuv4448BitFull, .yuv44410BitFull:
       return .full
     default:
       return .unknown

diff --git a/packages/react-native-vision-camera/ios/Extensions/Converters/AV+PixelFormat.swift b/packages/react-native-vision-camera/ios/Extensions/Converters/AV+PixelFormat.swift
@@ -44,6 +44,10 @@ extension PixelFormat {
       self = .yuv4448BitVideo
     case .yuv4448BitFull:
       self = .yuv4448BitFull
+    case .yuv44410BitVideo:
+      self = .yuv44410BitVideo
+    case .yuv44410BitFull:
+      self = .yuv44410BitFull
     case .rgbBgra8Bit:
       self = .rgbBgra8Bit
     case .rgbRgba8Bit:

diff --git a/...tive-vision-camera/ios/Extensions/CoreMedia/CMFormatDescription.MediaSubType+hidden.swift b/...tive-vision-camera/ios/Extensions/CoreMedia/CMFormatDescription.MediaSubType+hidden.swift
@@ -45,6 +45,11 @@ extension CMFormatDescription.MediaSubType {
     rawValue: kCVPixelFormatType_444YpCbCr8BiPlanarVideoRange)
   static let yuv4448BitFull = CMFormatDescription.MediaSubType(
     rawValue: kCVPixelFormatType_444YpCbCr8BiPlanarFullRange)
+  // YUV 4:4:4 10-Bit
+  static let yuv44410BitVideo = CMFormatDescription.MediaSubType(
+    rawValue: kCVPixelFormatType_444YpCbCr10BiPlanarVideoRange)
+  static let yuv44410BitFull = CMFormatDescription.MediaSubType(
+    rawValue: kCVPixelFormatType_444YpCbCr10BiPlanarFullRange)
 
   // BGRA
   static let rgbBgra8Bit = CMFormatDescription.MediaSubType(rawValue: kCVPixelFormatType_32BGRA)

diff --git a/...s/Constraints/ResolvableConstraint/ResolvableConstraint+VideoDynamicRangeConstraint.swift b/...s/Constraints/ResolvableConstraint/ResolvableConstraint+VideoDynamicRangeConstraint.swift
@@ -86,9 +86,11 @@ extension TargetColorSpace {
 extension CMFormatDescription.MediaSubType {
   fileprivate var colorRange: ColorRange {
     switch self {
-    case .yuv4208BitVideo, .yuv42010BitVideo, .yuv4228BitVideo, .yuv42210BitVideo:
+    case .yuv4208BitVideo, .yuv42010BitVideo, .yuv4228BitVideo, .yuv42210BitVideo,
+      .yuv4448BitVideo, .yuv44410BitVideo:
       return .video
-    case .yuv4208BitFull, .yuv42010BitFull, .yuv4228BitFull, .yuv42210BitFull:
+    case .yuv4208BitFull, .yuv42010BitFull, .yuv4228BitFull, .yuv42210BitFull,
+      .yuv4448BitFull, .yuv44410BitFull:
       return .full
     default:
       return .unknown
@@ -134,9 +136,11 @@ extension ColorRange {
 extension CMFormatDescription.MediaSubType {
   var bitDepth: DynamicRangeBitDepth {
     switch self {
-    case .yuv4208BitVideo, .yuv4208BitFull, .yuv4228BitVideo, .yuv4228BitFull:
+    case .yuv4208BitVideo, .yuv4208BitFull, .yuv4228BitVideo, .yuv4228BitFull,
+      .yuv4448BitVideo, .yuv4448BitFull:
       return .sdr8Bit
-    case .yuv42010BitVideo, .yuv42010BitFull, .yuv42210BitVideo, .yuv42210BitFull:
+    case .yuv42010BitVideo, .yuv42010BitFull, .yuv42210BitVideo, .yuv42210BitFull,
+      .yuv44410BitVideo, .yuv44410BitFull:
       return .hdr10Bit
     default:
       return .unknown