# Release Notes

## DepthAI V3

 * [DepthAI `3.8.0`](#DepthAI%203.8.0)
 * [DepthAI `3.7.1`](#DepthAI%203.7.1)
 * [DepthAI `3.6.1`](#DepthAI%203.6.1)
 * [DepthAI `3.5.0`](#DepthAI%203.5.0)
 * [DepthAI `3.4.0`](#DepthAI%203.4.0)
 * [DepthAI `3.3.0`](#DepthAI%203.3.0)
 * [DepthAI `3.2.1`](#DepthAI%203.2.1)
 * [DepthAI `3.1.0`](#DepthAI%203.1.0)
 * [DepthAI `3.0.0`](#DepthAI%203.0.0)
 * [DepthAIv3 `rc4`](#DepthAI%203.0.0rc4)
 * [DepthAIv3 `rc3`](#DepthAI%203.0.0rc3)
 * [DepthAIv3 `rc2`](#DepthAI%203.0.0rc2)
 * [DepthAIv3 `beta.1`](#DepthAI%203.0.0b1)
 * [DepthAIv3 `alpha.15`](#DepthAI%203.0.0a15)
 * [DepthAIv3 `alpha.14`](#DepthAI%203.0.0a14)
 * [DepthAIv3 `alpha.13`](#DepthAI%203.0.0a13)
 * [DepthAIv3 `alpha.12`](#DepthAI%203.0.0a12)
 * [DepthAIv3 `alpha.11`](#DepthAI%203.0.0a11)
 * [DepthAIv3 `alpha.10`](#DepthAI%203.0.0a10)
 * [DepthAIv3 `alpha.9`](#DepthAI%203.0.0a9)
 * [DepthAIv3 `alpha.8`](#DepthAI%203.0.0a8)

## DepthAI 3.8.0

Release date: July 11, 2026 Tag: `3.8.0`

Features:

 * Depth node * Unified API access to all depth sources (`StereoDepth`, `GPUStereo`, `NeuralDepth`, `NeuralAssistedStereo`, `ToF`)
    * Automatically selects the best possible depth source based on connected device features and user requirements such as FPS
      and resolution
    * C++ examples [here](https://github.com/luxonis/depthai-core/tree/main/examples/cpp/Depth) and Python examples
      [here](https://github.com/luxonis/depthai-core/tree/main/examples/python/Depth)
 * Device health check * Quickly get device diagnostics for device status, connection type, bandwidth, power supply, calibration,
   camera and IR sensor functionality, and any reported issues
    * C++ example [here](https://github.com/luxonis/depthai-core/blob/main/examples/cpp/Misc/HealthCheck/health_check.cpp) and
      Python example [here](https://github.com/luxonis/depthai-core/blob/main/examples/python/Misc/HealthCheck/health_check.py)
 * ToF node update * Support for RVC4 Lite with ToF
    * Unified API for both RVC2 and RVC4
    * New confidence output
    * C++ example [here](https://github.com/luxonis/depthai-core/blob/main/examples/cpp/ToF/tof_minimal.cpp) and Python example
      [here](https://github.com/luxonis/depthai-core/blob/main/examples/python/ToF/tof_minimal.py)
 * [RVC4] Default GPU backend for `ImageManip` * Improves performance and lowers power usage compared with the CPU backend
    * Support for image undistortion
 * [RVC4] Added support for OAK4 Lite and OAK4 Lite ToF * Recognition of OAK4 Lite devices
    * STMicro VD55H1 ToF sensor drivers and processing
 * Add support for YOLOv12
 * [RVC4] Added minimum- and maximum-range filtering to `NeuralDepth`
 * [RVC4] Added Unix system timestamps to all messages
 * [RVC4] Merge flashed CBA calibration with device EEPROM calibration * For each socket, prefer device EEPROM calibration if
   available; otherwise, use the calibration flashed to the CBA EEPROM
    * Flash the selected CBA EEPROM with calibration data
 * Add Multisensor Dynamic Calibration * Perform dynamic calibration between multiple sensors
 * Embedded Visualizer updated to 3.5.2: * Performance improvements for higher FPS
    * Improved PointCloud visualization
    * Visualization support for `Segmentation` messages
    * Visualization support for instance segmentation in `ImgDetections`

Misc:

 * Function argument cleanup: * Function arguments that are passed by value and then cloned are now passed by reference
    * Non-mutating functions are now `const`
 * `DetectionParser` can now be set up with `setNNArchiveHead` or via the `build` function, with the head passed as a parameter
 * `SegmentationParser` can now be set up with `setNNArchive` or `setNNArchiveHead`
 * Control the camera's maximum ISO for auto exposure with `setAutoExposureMaxISO`
 * Telemetry: * Support for Dynamic Calibration and Auto Calibration
    * Added rate limiting
 * [RVC2] Set the FSync delay for the 63D ToF sensor

Bug fixes:

 * The `specTranslation` vector is now set in `ImgTransformations` for all messages
 * Check whether the input file exists in the `Replay` node
 * [RVC4] Fix an issue where `Camera` node would drop a message only on full queues instead of all queues on the same output
 * [RVC4] PointCloud node uses the calibrated translation vector instead of the spec translation vector
 * [RVC2] Fix phase rotation for the 63D ToF sensor
 * [RVC2] Fix incorrect argument names for `Point2f` and `Size2f` in the Python bindings
 * [RVC2] FFC-4P now logs a warning if the number of sockets in the flashed calibration does not match the number of connected
   camera sockets

[RVC4] Luxonis OS compatibility: Integration tested with Luxonis OS 1.27.1, 1.30.1, and 1.33.0

Installation:

```bash
python3 -m pip install depthai==3.8.0
```

## DepthAI 3.7.1

Release date: June 7, 2026 Tag: `3.7.1`

Features:

 * [RVC4] New GPUStereo node * C++ example
   [here](https://github.com/luxonis/depthai-core/blob/v3.7.1/examples/cpp/GPUStereo/gpu_stereo.cpp) and Python example
   [here](https://github.com/luxonis/depthai-core/blob/v3.7.1/examples/python/RVC4/GPUStereo/gpu_stereo.py)
 * [RVC4] Add the GPU backend to `ImageManip` * Improves performance and lowers power usage compared to the CPU backend
    * This will be the default backend on RVC4 starting with `v3.8.0`
 * Embedded Visualizer updated to 2.5.3: * Improved pipeline debugging pane
 * Add a `Transformable` interface to messages to allow easy remapping from one coordinate system to another * Exposed as a
   `transformedMessage = message.transformTo(dai.ImgTransformations)`
    * Supported messages: `dai.ImgDetections`, `dai.SpatialImgDetections`, `dai.AprilTags`, `dai.Tracklets`,
      `dai.SegmentationMask`
 * Add telemetry to help us understand how the library is used so we can improve it * To opt out set `DEPTHAI_TELEMETRY=0` in the
   environment
 * Add support for 640x400 inputs to AutoCalibration, enabling more devices to be calibrated out of the box
 * [RVC4] Add support for INT16 inputs in `NeuralNetwork` node
 * [RVC4] Add sensor temperature metadata to `ImgFrame` when available
 * [RVC2] Add support for a new Samsung 63D ToF sensor

Misc:

 * [RVC2] Add support for CBA calibration reading and flashing
 * [RVC4] Unify color temperature behavior between RVC2 and RVC4
 * [RVC4] VPP and Neural assisted stereo can now run at 50 FPS @ 1280x800 improved from 27 FPS from before
 * [RVC4] Unify RVC4 IMU output to match RVC2 to never duplicate packets

Bug fixes:

 * Fix a rare issue on Windows where USB devices could fail to boot if discovery was running in another thread
 * Improve stability of the `.getAny` API on the `MessageQueue`
 * [RVC2] Fix a regression with magnetometer and rotation vector orientation on BNO086
 * [RVC4] Fix IMU timestamp drifting over time

[RVC4] Luxonis OS compatibility: Integration tested on Luxonis OS 1.20.5, 1.27.1 and 1.30.1

Installation:

```bash
python3 -m pip install depthai==3.7.1
```

### DepthAI 3.6.1

Release date: May 4, 2026 Tag: `3.6.1`

Features

 * AutoCalibration is now turned on by default and can be turned off with `DEPTHAI_AUTOCALIBRATION=OFF`
 * Add support for IMU calibration and unify outputs with each sensor now having a `RAW` `UNCALIBRATED` `CALIBRATED` * Important:
   `RAW` used to be pre-rotated to the RDF coordinate system, but was now changed to always be captured directly from the IMU. To
   keep the previous behavior please switch to the `UNCALIBRATED` output.
 * Add extrinsics tracking to ImgTransformations, along with utilities for remapping and projecting points between images * Each
   message now tracks its rotation and translation relative to the camera socket with the lowest index (for example, `CAM_A`)
    * C++ example [here](https://github.com/luxonis/depthai-core/blob/main/examples/cpp/Remapping/point_remapping.cpp) and Python
      [here](https://github.com/luxonis/depthai-core/blob/main/examples/python/Remapping/point_remapping.py)
 * Add YOLO26 support to DetectionParser
 * Add support for the new NeuralDepth models * Existing models with improved FPS * LARGE (768x480) from 10 FPS to 22
       * MEDIUM (576x360) from 26 FPS to 38
       * SMALL (480x300) from 42 FPS to 56
       * NANO (384x240) from 60 FPS to 85
    * New models added: * 1248x780 at 8.5 FPS
       * 1056x660 at 12.5 FPS
       * 960x600 at 14 FPS
       * 864x540 at 18 FPS
 * Add a new PointCloud node with support to select a custom coordinate system * C++ examples
   [here](https://github.com/luxonis/depthai-core/tree/main/examples/cpp/PointCloud) Python examples
   [here](https://github.com/luxonis/depthai-core/tree/main/examples/python/PointCloud)
 * Improve Holistic record & replay support * Record & replay also devices calibration
    * Record & mock device capabilities (`device.getConnectedCameraFeatures()` , `device.getConnectedIMU()`)
    * Auto sync the recordings for a more robust playback of the streams, when they need to be synced
    * Recording script [here](https://github.com/luxonis/depthai-core/blob/main/examples/python/RecordReplay/holistic_record.py),
      for replay, use `DEPTHAI_REPLAY={path to recording}` without needing to change the script.
 * Embedded Visualizer updated to 2.3.3: * Improved pipeline debugging pane
    * Small UI fixes
    * Improved device connection stability
 * Improve automatic Camera sensor config selection and FPS selection * Fallback on cropped configs when a full resolution config
   cannot satisfy requirements of the requested outputs
    * Automatically put cameras that cannot be FSynced with other cameras into free-running mode
    * Correctly track intrinsics for the cropped sensor configs * Note, on RVC4, LuxonisOS 1.31 or newer is required
 * Improve ObjectTracker with optional association in 3D and add velocity property to `dai.Tracklet`
 * [RVC4] Add support for PTP in Camera syncing on RVC4 * Supported on IMX586 and OG05 sensors
    * C++ example [here](https://github.com/luxonis/depthai-core/blob/main/examples/cpp/Remapping/point_remapping.cpp) Python
      example
      [here](https://github.com/luxonis/depthai-core/blob/main/examples/python/Misc/MultiDevice/multi_device_frame_sync.py)

Misc

 * Add `LEFT` and `RIGHT` alignment to StereoDepth and correctly respect `RECTIFIED_LEFT` and `RECTIFIED_RIGHT` on RVC4
 * [RVC2] Add support for IMX380
 * [RVC4] Use `SNPE 2.41.0.251128` if available for NeuralNetwork engine
 * Automatically switch DetectionParser to run on host in RVC2 in case the model contains a segmentation mask
 * Add support for `MessageDemux` to run on host

[RVC4] Luxonis OS compatibility

Integration tested on Luxonis OS 1.20.5, 1.27.1 and 1.30.1

Installation

```bash
python3 -m pip install depthai==3.6.1
```

### DepthAI 3.5.0

Release date: March 18, 2026 Tag: `3.5.0`

Features:

 * Add AutoCalibration node which automatically performs dynamic calibration * It can be turned on implicitly by setting the
   environment variable as `DEPTHAI_AUTOCALIBRATION=ON_START` or `CONTINUOUS`
    * The other option is to use it explicitly; C++ example
      [here](https://github.com/luxonis/depthai-core/blob/v3.5.0/examples/cpp/AutoCalibration/auto_calibration_example.cpp),
      Python example
      [here](https://github.com/luxonis/depthai-core/blob/v3.5.0/examples/python/AutoCalibration/auto_calibration_example.py)
 * Merge `v2.32.0` along with improvements on RVC2 in crashdump collection and device state retrieval

Misc:

 * Set tracked undistortion coefficients on legacy calibration to 0 when undistortion is turned on
 * Add `eventManager.waitForPendingUploads()` to avoid losing Snaps and Events that are waiting in the queue at script exit
 * Expand the stability test to include `NeuralAssistedStereo`, `FeatureTracker` and `ObjectTracker`

Installation:

```bash
python3 -m pip install depthai==3.5.0
```

### DepthAI 3.4.0

Release date: March 9, 2026 Tag: `3.4.0`

Features:

 * Add support for semantic segmentation
    * [C++ example](https://github.com/luxonis/depthai-core/blob/v3.4.0/examples/cpp/Segmentation/semantic_segmentation.cpp) and
      [Python example](https://github.com/luxonis/depthai-core/blob/v3.4.0/examples/python/Segmentation/semantic_segmentation.py)
 * Add support for ingesting instance segmentation in the SpatialLocationCalculator to improve 3D detections
    * [C++
      example](https://github.com/luxonis/depthai-core/blob/v3.4.0/examples/cpp/SpatialLocationCalculator/spatial_segmentation.cpp)
      and [Python
      example](https://github.com/luxonis/depthai-core/blob/v3.4.0/examples/python/SpatialLocationCalculator/spatial_segmentation.py)
 * Add support for spatializing keypoints into 3D
    * [Python
      example](https://github.com/luxonis/depthai-core/blob/v3.4.0/examples/python/SpatialLocationCalculator/spatial_keypoints.py)
 * [RVC4] Add support for USB protocol
    * Requires LuxonisOS 1.27.1 or newer
    * It can be forced with `DEPTHAI_PROTOCOL=usb` in the environment
 * Add `isp` output to Camera node
    * [C++ example](https://github.com/luxonis/depthai-core/blob/v3.4.0/examples/cpp/Camera/camera_isp.cpp) and [Python
      example](https://github.com/luxonis/depthai-core/blob/v3.4.0/examples/python/Camera/camera_isp.py)
 * Add Gate node
    * Enables easy opening and closing a message stream in runtime
    * [C++ example](https://github.com/luxonis/depthai-core/blob/v3.4.0/examples/cpp/Gate/gate_example.cpp) and [Python
      example](https://github.com/luxonis/depthai-core/blob/v3.4.0/examples/python/Gate/gate_example.py)
 * [RVC4] Add support for HFR (High frame rate) on IMX586:
    * 1280x720 @ 480 FPS
    * 1920x1080 @ 240 FPS
    * [C++ examples](https://github.com/luxonis/depthai-core/tree/v3.4.0/examples/cpp/HFR) and [Python
      examples](https://github.com/luxonis/depthai-core/tree/v3.4.0/examples/python/HFR)
 * Add support for XLink packetization
    * Optionally packetize messages sent through XLink and limit the bitrate per connection
    * Useful in advanced scenarios to allow streams with large messages to run in the background
    * Usage
      [example](https://github.com/luxonis/depthai-core/blob/ba7a920a2568ea6eaaaebf3f92bbdb40924187ae/tests/src/ondevice_tests/xlink_test.cpp#L70)
 * Visualizer updated to 2.0.10
    * Support for live pipeline visualization when `DEPTHAI_PIPELINE_DEBUGGING=ON` is set
    * Visualize keypoints when showing `ImgDetections`
    * Automatically remap detections and annotations to the target stream
 * Add a new `CalibrationMetrics` output to DynamicCalibration node
 * Add support for a callback for Snaps & Events to get notified when an event gets sent to Hub
   [example](https://github.com/luxonis/depthai-core/blob/v3.4.0/examples/python/Events/events.py)
 * [RVC4] Add support for external FSync
    * [C++
      example](https://github.com/luxonis/depthai-core/blob/v3.4.0/examples/cpp/Misc/MultiDevice/multi_device_external_frame_sync.cpp)
      and [Python
      example](https://github.com/luxonis/depthai-core/blob/v3.4.0/examples/python/Misc/MultiDevice/multi_device_external_frame_sync.py)
 * [RVC2] Add support for setting custom sensor tuning per sensor
 * [RVC2] Add support for setting sensor orientation in the Camera node

Bug fixes:

 * Fix ownership when `dai::Pipeline` is copy-assigned to another variable
 * Fix replay for `StereoDepth` for the case where `ImgTransformations` aren't set

Misc:

 * Deprecate creating nodes without `pipeline.create`
 * Make basalt a private dependency instead of public
 * ImageAlign: * Warn if a distorted image is sent to `ImageAlign`'s `alignTo`
    * Use `ImgTransformations` to get intrinsics and distortion coefficients instead of relying on heuristics and global
      calibration
 * [RVC4] Add support for RVC4 devices to DeviceManager
 * [RVC2] Add new fields to `ImgDetections` inside `Script` node bindings

[RVC4] Luxonis OS compatibility: Integration tested on Luxonis OS 1.14.1, 1.20.5 and 1.27.1

Installation:

```bash
python3 -m pip install depthai==3.4.0
```

### DepthAI 3.3.0

Release date: January 16, 2026 Tag: `3.3.0`

Features

 * Add Pipeline Debugging support * More details can be found in the
   [README](https://github.com/luxonis/depthai-core/tree/v3.3.0/PipelineDebugging.md)
    * The pipeline graph can be visualized with [depthai_pipeline_graph](https://github.com/luxonis/depthai_pipeline_graph)
    * C++ examples [here](https://github.com/luxonis/depthai-core/tree/v3.3.0/examples/cpp/Misc/PipelineDebugging) and Python
      examples [here](https://github.com/luxonis/depthai-core/tree/v3.3.0/examples/python/Misc/PipelineDebugging)
 * Add NeuralAssistedStereo node (classical stereo + neural depth fusion) * Uses VPP internally to fuse the classical stereo depth
   with neural depth
    * C++ examples [here](https://github.com/luxonis/depthai-core/tree/v3.3.0/examples/cpp/NeuralAssistedStereo) and Python
      examples [here](https://github.com/luxonis/depthai-core/tree/v3.3.0/examples/python/NeuralAssistedStereo)
 * Add VPP node and configuration API * C++ examples [here](https://github.com/luxonis/depthai-core/tree/v3.3.0/examples/cpp/Vpp)
   and Python examples [here](https://github.com/luxonis/depthai-core/tree/v3.3.0/examples/python/Vpp)
 * Expose XLinkBridges * For advanced use-cases, to configure the implicit XLink bridges created when crossing host-device
   boundary
    * C++ example [here](https://github.com/luxonis/depthai-core/tree/v3.3.0/examples/cpp/Misc/XLinkBridge) and Python example
      [here](https://github.com/luxonis/depthai-core/tree/v3.3.0/examples/python/Misc/XLinkBridge)
 * Add Housing calibration support to `CalibrationHandler`
 * [RVC4] Add SystemLogger node and expanded SystemInformation metrics * C++ example
   [here](https://github.com/luxonis/depthai-core/tree/v3.3.0/examples/cpp/Misc/SystemLogger) and Python example
   [here](https://github.com/luxonis/depthai-core/tree/v3.3.0/examples/python/Misc/SystemLogger)
 * [RVC4] Update `StereoDepth` presets on RVC4 with improved quality/fillrate trade-offs

Bug fixes and stability

 * Fix SSD parser regression and add `labelName` support in keypoints/detections
 * Fix file corruption when recording long videos with H264 encoding with `Record` node
 * [RVC4] Turn off Nagle's algorithm to avoid latency spikes on Windows
 * [RVC4] Fix a race condition in StereoDepth node changing the left and right input frames
 * [RVC4] Fix camera mapping for custom RVC4 boards
 * [RVC2] Fix an edge case for MessageGroup's cache coherency
 * [RVC2] Remove a false alarm warning in SpatialDetectionNetwork when input image was rotated

Misc

 * Add binary services support to `RemoteConnection` and configurable callback thread count
 * Add resize mode to build method in `NeuralNetwork`, `DetectionNetwork` and `SpatialDetectionNetwork` nodes
 * Add support for more frame types in `ImgFrame.setCvFrame()`
 * [RVC4] Add support for manual white-balance
 * [RVC4] Turn off dot projectors when pipeline stops
 * [RVC4] Add temporal filter to NeuralDepth node

[RVC4] Luxonis OS compatibilityIntegration tested on Luxonis OS 1.14.1, 1.18.3 and 1.23.1

Installation:

```bash
python3 -m pip install depthai==3.3.0
```

### DepthAI 3.2.1

Release date: November 28, 2025  Tag: `3.2.1`

Features

 * Extend `DetectionParser` and `ImgDetections` message with instance segmentation and keypoints parsing
    * Keypoints run on device for both RVC2 and RVC4
    * Instance segmentation runs on device for RVC4 and on host for RVC2
    * C++ examples [here](https://github.com/luxonis/depthai-core/tree/v3.2.0/examples/cpp/DetectionNetwork) and Python examples
      [here](https://github.com/luxonis/depthai-core/tree/v3.2.0/examples/python/DetectionNetwork)
 * Add support for the new Snaps&Events API:
    * Example for C++ [here](https://github.com/luxonis/depthai-core/tree/v3.2.0/examples/cpp/Events) and for Python
      [here](https://github.com/luxonis/depthai-core/tree/v3.2.0/examples/python/Events)
 * [RVC4] Add NeuralDepth node supporting the neural depth running on device
    * Supported on Luxonis OS 1.20.4 and newer
    * Four sizes supported * LARGE → 768x480 @ 10.8 FPS
       * MEDIUM → 576x360 @ 25.5 FPS
       * SMALL → 480x300 @ 42.5 FPS
       * NANO → 384x240 @ 59.7 FPS
    * Examples for C++ [here](https://github.com/luxonis/depthai-core/tree/v3.2.0/examples/cpp/NeuralDepth) and for Python
      [here](https://github.com/luxonis/depthai-core/tree/v3.2.0/examples/python/NeuralDepth)
 * [RVC4] Switch the front LED to green when DepthAI is running
 * [RVC2] Add tuning for the IMX577 sensor, removing the previously present blue tint

Bug fixes and stability

 * Fix an edge case for IPv4LL discovery on MacOS
 * [RVC4] Fix a small memory leak on RVC4 happening in Camera node and in StereoDepth when extended mode is enabled
 * [RVC2] Fix a rare issue of IMU preventing a device reboot
 * [RVC2] Patch ToF calibration that caused a minor bump in readout values in the middle of the frame
 * [RVC4] Fix a regression for IMX586 only working with the 4000×3000 sensor config @30 FPS

Misc

 * Add HDR examples for C++ [here](https://github.com/luxonis/depthai-core/blob/v3.2.0/examples/cpp/Camera/camera_hdr.cpp) and
   Python [here](https://github.com/luxonis/depthai-core/blob/v3.2.0-rc.0/examples/python/Camera/camera_hdr.py)
 * Add priority implementation to `RemoteConnection` to prioritize metadata over raw frames
 * Expose an embedded RPC on `RemoteConnection` called `libraryVersion` which returns the DepthAI version
 * Embedded visualizer is updated from `0.12.33` to `1.5.40`
 * Stop extracting NeuralNetwork models to a temporary directory to reduce disk usage
 * [Python] Remove warnings on MacOS for duplicate symbols for `CVSlider` `CVWindow` when library is used alongside `cv2`
 * [Python] Add support for Python3.14 and drop Python3.8
 * [RVC4] Add support for flashing and reading housing calibration
 * [RVC4] Refactored Camera stack with improved stability for startup and restarts
    * Improves stability for multi-day runs
    * Solves a rare case of camera getting stuck and unable to stream which required a device reboot
 * [RVC4] Handle the timestamp change that will be present in LuxonisOS 1.21.0
 * [RVC4] Add a `device.getProcessMemoryUsage()` returning memory usage of just the `depthai-device` process
 * [RVC2] Add bindings for `setTransformation` in Python bindings for Script node
 * [RVC2] Allow DynamicCalibration to run on devices with older calibration with un-distortion disabled
 * [RVC2] Autodetermine pool sizes to allow high resolution frames on IMX582 to run without explicit changes
 * [RVC2] Improved handling of HDR for IMX582
    * Limit the FPS to 10

On LuxonisOS 1.20.5+, up to 240 FPS is now supported.

Installation:

```bash
python3 -m pip install depthai==3.2.1
```

### DepthAI 3.1.0

Release date: October 20, 2025 Tag: `3.1.0`

Features

 * Automatically select the number of pools in Camera node * Improves the performance at high resolutions for OAK1-Max
 * Implement the maximum exposure cap in AE on RVC4 * Requires Luxonis OS v1.19.1
 * Add setters to `PointCloudData` message * C++ example
   [here](https://github.com/luxonis/depthai-core/blob/main/examples/cpp/RGBD/rgbd_pcl_processing.cpp)
    * Python example [here](https://github.com/luxonis/depthai-core/blob/main/examples/python/RGBD/rgbd_pcl_processing.py)

Bug fixes

 * Address MacOS weak vtables issues causing deadlocks in the new `DynamicCalibration` node
 * Turn on the watchdog early during discovery of RVC2 USB devices to avoid soft bricking the device along with handling the case
   where the device gets into that state to recover it on the next boot
 * Fix the usage of RVC2 devices inside Linux containers because of missing udev support
 * Fix undistortion on RVC4 for the chroma plane when `NV12` type is requested
 * Use the correct `ImgTransformations` in SpatialDetectionNetwork on RVC4 in case depth was not aligned to RGB
 * Stability fixes for rare case with IMU halting the destruction on RVC2
 * Fix a timestamp overflow bug on the BNO08x IMU on RVC2

Misc

 * Update `zoo_helper` binary with better error handling
 * Reduce the number of symbols on Windows by performing more aggressive inlining
 * `DynamicCalibration` input control now has a shorter API to send commands to the node
 * Add intrinsics metadata to thermal frames
 * Update the examples using `StereoDepth` node with removing the explicit `NV12` type request for better performance
 * Improve IMX678 support on RVC2 with better black level correction, improving brightness and color accuracy
 * [Python bindings] Add explicit `numpy` requirement to the Python wheels
 * [Python bindings] Add missing bindings to set the filter order on the `StereoDepth` node

Installation:

```bash
python3 -m pip install depthai==3.1.0
```

### DepthAI 3.0.0

Release date: September 8, 2025 Tag: `3.0.0`

DepthAI v3.0.0 release is out

We're proud to announce a new major revision of the DepthAI library is now out of the release candidate stage and is fully
released as v3.0.0!

Simplified API: We've simplified and unified the API to lower the barrier to entry and make development more intuitive. Core tasks
like setting up camera streams, running neural networks, and building spatial pipelines are now streamlined with fewer lines of
code.

We have removed many deprecated functions and simplified node constructors, creating a cleaner, more consistent, and easier-to-use
library for newcomers as well as more experienced users.

Refreshed nodes: We've revisited some of the most fundamental nodes to make them more powerful and flexible.

 * Camera
    * The `ColorCamera` and `MonoCamera` nodes have been replaced by a single, generic `Camera` node that works across all
      platforms.
    * It supports a variable number of outputs, where each can have an independent: * Type (NV12, RGB interleaved or planar, ...)
       * Size
       * FPS
    * [Python](https://github.com/luxonis/depthai-core/tree/main/examples/python/Camera) and
      [C++](https://github.com/luxonis/depthai-core/tree/main/examples/cpp/Camera) examples.
 * ImageManip
    * The `ImageManip` node has been revised for more robust and predictable behavior (we now track the order of operations to
      make the output fully deterministic).
    * It now supports relative crops and can be used as a host-side node in addition to running on RVC2 and RVC4 devices.
    * [Python](https://github.com/luxonis/depthai-core/tree/main/examples/python/ImageManip/) and
      [C++](https://github.com/luxonis/depthai-core/tree/main/examples/cpp/ImageManip/) examples.

New nodes: DepthAI v3 introduces new high-level nodes to simplify working with high level concepts (RGBD pointclouds, SLAM) as
well as a node to perform dynamic calibration of stereo cameras.

 * RGBD: This node makes it easy to work with synchronized and aligned color and depth data. It features an autocreate mode that
   automatically constructs the required input pipeline, delivering a ready-to-use RGBD message or a colored point cloud. *
   [Python](https://github.com/luxonis/depthai-core/tree/main/examples/python/RGBD) and
   [C++](https://github.com/luxonis/depthai-core/tree/main/examples/cpp/RGBD) examples.
 * VSLAM: We've added SLAM and VIO as host nodes, enabling advanced spatial AI applications. These are currently available on
   Linux and macOS and are in early preview. * [Python](https://github.com/luxonis/depthai-core/tree/main/examples/python/VSLAM)
   and [C++](https://github.com/luxonis/depthai-core/tree/main/examples/cpp/VSLAM) examples.
 * DynamicCalibration: This node performs dynamic calibration of stereo cameras, allowing you to achieve accurate depth perception
   even under high thermal and mechanical stress applied to the device. *
   [Python](https://github.com/luxonis/depthai-core/tree/main/examples/python/DynamicCalibration) and
   [C++](https://github.com/luxonis/depthai-core/tree/main/examples/cpp/DynamicCalibration)

Support for host nodes: DepthAI v3 now supports custom host nodes, allowing you to run parts of your pipeline on the host with
custom logic while keeping the rest on-device. Whether you need to run complex post-processing in Python or integrate with
external libraries, it's all part of the same unified pipeline. See the
[Python](https://github.com/luxonis/depthai-core/tree/main/examples/python/HostNodes) and
[C++](https://github.com/luxonis/depthai-core/tree/main/examples/cpp/HostNodes) examples.

Visualizer: Debugging and development just got easier with our new integrated visualizer. You can now visualize camera streams,
neural network outputs, and detection overlays in real-time. The visualizer is also able to display the pipeline graph, making it
a great tool for understanding and debugging your application's data flow. See the
[Python](https://github.com/luxonis/depthai-core/tree/main/examples/python/Visualizer) and
[C++](https://github.com/luxonis/depthai-core/tree/main/examples/cpp/Visualizer) examples.

A lot of nice to have features::

 * Auto reconnect: If a device has a flaky connection and crashes, the library will now automatically try to reconnect instead of
   exiting, making your applications more resilient.
 * Unified Coordinate System: We've standardized all coordinate systems. Camera, IMU, and spatial data now use the RDF
   (Right-Down-Forward) convention, eliminating inconsistencies when fusing data from multiple sensors.
 * Native Model Zoo Support: Take advantage of the new Luxonis Model Zoo, which integrates natively into v3. Loading and deploying
   models is now seamless, with no boilerplate required.
 * Remapping points between different frames: We've greatly improved the developer experience where detections from one image in
   the pipeline (on the input of the NN for example) need to be remapped to another image in the pipeline, that's still in full
   resolution by internally tracking all of the image operations that are applied to streams. See
   [Python](https://github.com/luxonis/depthai-core/blob/main/examples/python/ImageManip/image_manip_remap.py) and
   [C++](https://github.com/luxonis/depthai-core/blob/main/examples/cpp/ImageManip/image_manip_remap.cpp) examples.

Support for RVC4 devices: DepthAI v3 brings support for both RVC2 and RVC4 devices, with a unified codebase that runs on both
platforms. This allows you to prototype on one and deploy on another without code changes in most cases.

Migration from v2.x version of the library: We've prepared a porting guide to speed up the migration
[here](https://github.com/luxonis/depthai-core/blob/main/V2V3PortinGuide.md).

Known issues:

 * On release flavors of the Luxonis OS on RVC4, the camera stack can get stuck in a bad state where cameras do not restart
   streaming, requiring a device reboot. It is recommended to use `-debug` versions of the OS until this is resolved.

What's changed since v3.0.0-rc4

New features:

 * DynamicCalibration node * Performs dynamic calibration on the camera to compensate for thermal and mechanical stress
    * Examples in [Python](https://github.com/luxonis/depthai-core/blob/main/examples/python/DynamicCalibration) and
      [C++](https://github.com/luxonis/depthai-core/blob/main/examples/cpp/DynamicCalibration)
 * Add support for a new revision of OAK-Thermal (R8)
 * Add host implementation to `ImageAlign` enabling higher FPS in pipelines that are partly running on host
 * Add a [depthai-core-example](https://github.com/luxonis/depthai-core-example) project reference in README.md
 * Add `ImgTransformations` tracking to `ObjectTracker` *
   [example](https://github.com/luxonis/depthai-core/blob/main/examples/python/ObjectTracker/object_tracker_remap.py)

Bug fixes and stability improvements:

 * Fix a crash on RVC2 when a device is partially calibrated
 * Fix pink streams on small resolutions on OAK-D[-Pro]-Wides with the OV9728 sensor
 * Fix a regression for replay that caused the first set of frames to be invalid
 * Fix the rotation of the IMU rotation vector on RVC2
 * Fix RVC4 Camera not being able to stream without calibration
 * Fix a rare startup bug for ImageAlign on RVC4 where DSP failed to load the required module
 * Fix an edge case in ImageManip node on RVC4 failing to resize to desired resolution(s)

Misc:

 * Add a way to set sensor type (color/mono) on the Camera node on RVC4 with `.setSensorType()` * Allows quick switching and
   testing for OV9[2/7]82 sensors
 * Improve ToF decoding performance on RVC2 to allow 30 FPS decoding
 * Add ImgTransformations tracking in case of no calibration for a single source stream
 * Add tests for `CalibrationHandler`
 * Move the Python utilities to the root of the repository
 * Add a test tag for the OAK4-S and make a test run for the OAK4-S on CI
 * Combine the Python wheels (all python versions per architecture combined in one wheel) for a smaller size footprint on PyPi
 * Improve the responsiveness of Python bindings to interrupts
 * Improve the performance of the ToF node and examples; they now run at 30 FPS

Installation:

```bash
python3 -m pip install depthai==3.0.0
```

### DepthAI 3.0.0rc4

Release date: July 31, 2025 Tag: `3.0.0-rc4`

Features:

 * Added ObjectTracker node on RVC4 which can also run as a host node. * Based on OC-Sort algorithm
    * Improved performance compared to the RVC2 implementation
    * [Examples](https://github.com/luxonis/depthai-core/tree/main/examples/python/ObjectTracker)
 * Added support for runtime calibration changes on RVC4
 * Support for undistorted outputs in Camera node on RVC4 *
   [Example](https://github.com/luxonis/depthai-core/blob/main/examples/python/Camera/camera_undistortion.py)
 * Added ToF Filtering * Greatly reduces noise and improves quality
    * Filtering is enabled by default on the ToF node
    * The filters currently run on the host
    * The filtering can also be used independently with the new ImageFilters node
    * [Example](https://github.com/luxonis/depthai-core/blob/main/examples/python/RVC2/ToF/tof_minimal.py)

Bug fixes:

 * Fixed an issue where using OV9728 at resolutions smaller than 640x400 forced a mono-only sensor config on RVC2
 * Stabilized internal camera clock and monotonic clock syncing
 * Fixed the Camera->IMU extrinsics setting in BasaltVIO node
 * Fixed an edge case where dai.Device constructor could get stuck indefinitely if the device lost connection at the wrong time by
   adding a timeout internally

Misc:

 * Removed the deprecated imageIn input on DetectionParser which has been replaced by using ImgTransformations
 * Skipped file locking for Zoo model downloads when filesystem is read-only
 * getCalibration always returns the current active calibration, even when not set by setCalibration
 * Changed the RGBD autocreate logic to use ToF depth on OAK-ToF instead of stereo.
 * Added ToF RGB align [example](https://github.com/luxonis/depthai-core/blob/main/examples/python/RVC2/ToF/tof_align.py)
 * Added a convenience getNNArchive getter to NeuralNetwork node

RVC4 OS comaptibility:

 * Integration tested on Luxonis OS 1.6.0-debug, 1.14.1-debug and 1.15.0-debug

Known issues / caveats::

 * On release flavors of the OS on RVC4, the camera stack can get stuck in a bad state, where cameras don't start streaming again
   and a reboot is needed * It is recommended to use -debug versions of the OS, until this is resolved

Installation:

```bash
python3 -m pip install depthai==3.0.0rc4
```

### DepthAI 3.0.0rc3

Release date: July 11, 2025 Tag: `3.0.0-rc3`

Features:

 * Optimized XLink memory usage on RVC2 allowing for larger pipelines without running out of memory
 * Added support for the latest revision of the OAK-ToF (R4)

Bug fixes:

 * Edge case in ToF decoding overflow fixed
 * Fixed a regression on DSP post-processing in Stereo node on RVC4
 * Addressed the camera timestamp drift on RVC4
 * `CalibrationHandler.getCameraExtrinsics()` regression fixed by flipping the matrix multiplication order
 * Fixed a possible race condition in ImageManip in `LOW_POWER` mode on RVC4

Misc:

 * Added missing bindings for `RotatedRect` in Script node on RVC2
 * Switched to standardized access for EEPROM on RVC4 platform
 * Switched to `std::filesystem::path` from `dai::Path` throughout the codebase
 * Added unique input names by default making multi-input host nodes work without the need to explicitly name inputs/outputs
 * Added examples for EdgeDetector and SystemLogger
 * Added filesystem locks for Zoo model downloading for multi-process usage
 * Added support for parallel Debug and Release builds on Windows (previous limitation due to vcpkg)

RVC4 OS compatibility:

 * Integration tested on Luxonis OS 1.2, 1.6.0-debug and 1.14.1-debug

Known issues / caveats:

 * On release flavors of the OS on RVC4, the camera stack can get stuck in a bad state, where cameras don't start streaming again
   and a reboot is needed * It is recommended to use -debug versions of the OS, until this is resolved

Installation:

```bash
python3 -m pip install depthai==3.0.0rc3
```

### DepthAI 3.0.0rc2

Release date: 11th June 2025 Tag: `3.0.0-rc2`

What's new:

 * Pre-rotated the IMU outputs to the RH coordinate system so from the perspective of the camera the axis are: * X pointing right
    * Y pointing down
    * Z pointing to front (out of the glass)
 * Updated dependencies to support latest compilers and CMake 4
 * Forward ported the setCalibration and getCalibration functions on RVC2 to support dynamic calibration

Bug fixes:

 * Fix a regression in ImageManip node on RVC4 introduced on beta.1
 * Fix a regression in Camera resizers

RVC4 OS compatibility

 * Integration tested on Luxonis OS 1.2, 1.6.0-debug and 1.11.0-debug

Known issues / caveats:

 * On release flavors of the OS on RVC4, the camera stack can get stuck in a bad state, where cameras don't start streaming again
   and a reboot is needed
 * It is recommended to use -debug versions of the OS, until this is resolved

Installation:

```bash
python3 -m pip install depthai==3.0.0rc2
```

(the first v3 release that was pushed to PyPI!)

### DepthAI 3.0.0b1

Release date: May 23, 2025 Tag: `3.0.0-beta.1`

What's new:

 * Missing C++ were added to match the Python examples
 * Add support for C++ integration of the library
 * Add low power mode to ImageManip on RVC4
 * Lower resource usage for OAK-D-Lite IMX214, much improving the experience with the Lite on v3
 * Add support for very small outputs out of Camera node on RVC2
 * Add support for all resize modes on Camera node on RVC4 (letter box, scale, crop)
 * Turn off luma de-noising on stereo sensors by default on RVC4 to improve Stereo performance
 * Add a new field name to ImgDetections and SpatialImgDetections
 * Embedded visualizer bumped to 0.12.33

Bug fixes:

 * Fix embedded FE serving on Windows for Visualizer
 * Don't uploaded assets to Visualizer when showing the pipeline graph

Breaking changes:

 * Yolo/Mobilenet variations of [Spatial]DetectionNetwork were removed.
 * ColorCamera and MonoCamera were deprecated
 * ImageManipV2 was renamed to ImageManip and the old ImageManip was removed
 * Deprecated alternatives to initialConfig on all nodes were removed
 * [C++ only] - initialConfigs on applicable nodes are now held by std::shared_ptr
 * Spatial nodes now output results in right hand coordinate system

RVC4 OS compatibility

 * Integration tested on Luxonis OS 1.2, 1.6.0-debug and 1.11.0-debug

Known issues / caveats:

 * On release flavors of the OS on RVC4, the camera stack can get stuck in a bad state, where cameras don't start streaming again
   and a reboot is needed * It is recommended to use -debug versions of the OS, until this is resolved

To install:

```bash
python3 -m pip install --extra-index-url https://artifacts.luxonis.com/artifactory/luxonis-python-release-local/ depthai==3.0.0b1
```

#### DepthAI 3.0.0a15

Release date: April 15, 2025Tag: `3.0.0-alpha.15`

 * New
    * Full support for MJPEG and H26x encoders from non‑camera sources on RVC4.
    * Added RGBD node with both color point‑cloud output and combined RGB‑D message. * Supports autocreate mode to auto‑align RGB
      and depth.
       * [Examples ↗](https://github.com/luxonis/depthai-core/tree/v3.0.0-alpha.15/examples/python/RGBD)
    * Holistic Record & Replay (early access) — convert examples to record/replay without changing source code. * Early‑access
      limitation: device‑capability mocking not yet implemented; replay for stereo or advanced examples must run on the same
      device.
       * [Examples ↗](https://github.com/luxonis/depthai-core/tree/v3.0.0-alpha.15/examples/python/RecordReplay)
    * Device discoverability in setup mode with guidance to [setup.luxonis.com](https://setup.luxonis.com).
    * HDR support for IMX586 on RVC4. * Works on OAK4‑S; requires a forthcoming Luxonis OS update for OAK4‑D / OAK4‑Pro.
       * Enable with `camera.initialControl.setHdr(True)` (runtime configurable).
    * DSP implementation for StereoDepth algorithms (filters, LR‑check, disparity to depth conversion) on RVC4.
    * NeuralNetwork node now copies ImgTransformations to additional inputs in multi‑input models when only one input defines
      them.
    * Embedded visualizer bumped to v0.9.20.
 * Bug fixes
    * Prevent dead‑lock edge‑cases when adding callbacks to queues at runtime.
    * Fix `dai.ImgAnnotations` casting error on Windows.
    * Address undistortion edge‑cases in Camera node.

Known issues / caveats On release flavors of Luxonis OS for RVC4 the camera stack can stall, requiring a reboot for streams to
resume.Until fixed, use `‑debug` OS images.

Integration tested on [Luxonis OS 1.2, 1.4.1, 1.5.0 and 1.6.0‑debug](https://docs.luxonis.com/software-v3/sw-stack/luxonis-os.md),
but we recommend using latest (1.6-debug). You can Install this DepthAIv3 version using this command:

```bash
python3 -m pip install --extra-index-url https://artifacts.luxonis.com/artifactory/luxonis-python-release-local/ depthai==3.0.0a15
```

#### DepthAI 3.0.0a14

 * New: * Added support for 48MP (8000x6000) resolution on OAK4 cameras ([example
   here](https://docs.luxonis.com/software-v3/depthai/examples/camera/camera_still_max_res.md)). Current limitations: * Only one
   additional camera can run in parallel with 48MP
       * Only one output (full-res) can be requested from the Camera node. Please use ImageManip to create additional streams.
    * ROI-based auto-exposure and auto-focus for OAK4 cameras, [example
      here](https://docs.luxonis.com/software-v3/depthai/examples/camera/camera_roi_exposure_focus.md)
    * Camera node now supports `raw` output, [example
      here](https://docs.luxonis.com/software-v3/depthai/examples/camera/camera_raw.md)
    * Greatly improved connection time on OAK4 cameras (needs OS 1.5 or newer)
 * Bug fixes: * Fix `CameraSocker not found` issue that sometimes happened when starting the pipeline

Integration tested on [Luxonis OS 1.2, 1.4.1, 1.5 and 1.6](https://docs.luxonis.com/software-v3/sw-stack/luxonis-os.md), but we
recommend using latest (1.6). You can Install this DepthAIv3 version using this command:

```bash
python3 -m pip install --extra-index-url https://artifacts.luxonis.com/artifactory/luxonis-python-release-local/  depthai==3.0.0a14
```

#### DepthAI 3.0.0a13

 * New: * Initial [FeatureTracker node](https://docs.luxonis.com/software-v3/depthai/depthai-components/nodes/feature_tracker.md)
   implementation for RVC4
    * [Warp node](https://docs.luxonis.com/software-v3/depthai/depthai-components/nodes/warp.md) now works with RVC4
    * Added features for [StereoDepth node](https://docs.luxonis.com/software-v3/depthai/depthai-components/nodes/stereo_depth.md)
      RVC4: * Split filtering in a separate thread to improve throughput
       * Turn off software LR check and software thresholding by default
       * Now runs at 60FPS for 800P (with LR check enabled), 55FPS for both LR check + Extended disparity
 * Bug fixes: * [ImageManip node](https://docs.luxonis.com/software-v3/depthai/depthai-components/nodes/image_manip.md) on RVC4
   fix for Windows
    * Fix issues with excessive logging

Integration tested on [Luxonis OS 1.4.1](https://docs.luxonis.com/software-v3/sw-stack/luxonis-os.md), but should work on anything
above version 1.2. You can Install this DepthAIv3 version using this command:

```bash
python3 -m pip install --extra-index-url https://artifacts.luxonis.com/artifactory/luxonis-python-release-local/  depthai==3.0.0a13
```

#### DepthAI 3.0.0a12

 * New: * Manual focus support on RVC4
    * Initial IMU support on RVC4
    * Added [BenchmarkIn](https://docs.luxonis.com/software-v3/depthai/depthai-components/nodes/benchmark_in.md) and
      [BenchmarkOut](https://docs.luxonis.com/software-v3/depthai/depthai-components/nodes/benchmark_out.md) nodes for both RVC2
      and RVC4
    * Undistortion support added for [Camera
      node](https://docs.luxonis.com/software-v3/depthai/depthai-components/nodes/camera.md) on RVC2 (WIP for RVC4)
    * Improved [NeuralNetwork](https://docs.luxonis.com/software-v3/depthai/depthai-components/nodes/neural_network.md)
      implementation for multiple threads on RVC4. Before, multiple threads didn't provide better performance, while NN node now
      matches `snpe-throughput-run` performance when both are run with the same number of threads.
 * Bug fixes: * Error out verbosely nicer when unsupported color conversion is requested from
   [ImageManip](https://docs.luxonis.com/software-v3/depthai/depthai-components/nodes/image_manip.md) on RVC4
    * Avoid duplication of NN models in memory on RVC4 (now it's possible to run 1.7GB NN model on RVC4)

Integration tested on [Luxonis OS 1.2 and 1.3](https://docs.luxonis.com/software-v3/sw-stack/luxonis-os.md), Install using this
command:

```bash
python3 -m pip install --extra-index-url https://artifacts.luxonis.com/artifactory/luxonis-python-release-local/  depthai==3.0.0a12
```

#### DepthAI 3.0.0a11

 * New: * Crashdump collection for both RVC2 and RVC4
    * New stereo filters from v2.29.0
    * Added `.io` input/output map to Script node on RVC4 to match the legacy API of the RVC2
 * Bug fixes: * Fix `ImageManip`: resizing size off by 1 bug, fix operation where image is reused
    * Fix multiple GIL issues that caused deadlocks on device/pipeline destruction

Integration tested on [Luxonis OS 1.2](https://docs.luxonis.com/software-v3/sw-stack/luxonis-os.md), initial tests with 0.26.
Install using this command:

```bash
python3 -m pip install --extra-index-url https://artifacts.luxonis.com/artifactory/luxonis-python-release-local/  depthai==3.0.0a11
```

#### DepthAI 3.0.0a10

Alpha.10 is mosty just a patch release.

 * Bug fixes: * Fix the manylinux wheels
    * Patch calibration for an early run of OAK4-Ds with missing extrinsics for the RGB camera and removing cyclic connections
    * Fix the case when multiple callbacks are added to a single queue

Integration tested on Luxonis OS 0.25, expected to work with 0.26 as well.

Luxonis OS 1.0 does not work with DAI due to a bug in camera discovery and neither does the device setup

#### DepthAI 3.0.0a9

> **Bug on Linux**
> Linux wheels only worked on Python3.12. If you are using Linux, either use Python3.12 or use newer wheels from the next release.

Released December 2, 2024. Compatible with [Luxonis OS 0.25](https://docs.luxonis.com/software-v3/sw-stack/luxonis-os.md).

 * What's new: * ImageAlign node on RVC4
    * Add an overridable getVisualizationMessage function to messages to be able to bind the visualization per message for custom
      parsers, etc.
    * Improved handling in CalibrationHandler which now detects cyclic extrinsics.
    * Update NNArchiveConfig definition to latest and respect the new daiType field if it's set.
    * Added Python3.13 wheels for all platforms.
    * Updated the embedded visualizer
 * Bug fixes: * Fix passthroughs outputs with multi-input NN on RVC4
    * Fix ImageManip issues with setting the output size on RVC2, RVC4 and Host
    * Fix ImageManip issues with runtime config changes on RVC2
 * Misc: * Add missing bindings for `dai.Point2f` constructors which explicit normalize flag
    * For RVC4 alpha.9 was integration tested on Luxonis OS 0.25 but is expected to run fine on 0.26 and 1.0 as well.

#### DepthAI 3.0.0a8

Released December 2, 2024. Compatible with [Luxonis OS 0.25](https://docs.luxonis.com/software-v3/sw-stack/luxonis-os.md).

 * What's new: * Custom RPCs added to `dai.RemoteConnection`
    * Lift the limitation of the message size on the host->device bridge on RVC4 to virtually unlimited
    * Wheels sizes reduced by ~50%
    * Support for fine grained FPS on RVC4 (OS 0.25 required) * OV9282: 3.0 - 60.0 FPS
       * IMX586: 2.0 - 30.0 FPS
    * Support for the Luxonis OS 0.25 and above
 * Bug fixes: * Fix support for combined multi-input using `NNData` on RVC4
 * Misc: * Hunter was removed and replaced with `vcpkg`

## DepthAI V2

This is the v2 version of DepthAI, which doesn't support RVC4 devices.

 * [DepthAI 2.32.0](#DepthAI%202.32.0)
 * [DepthAI 2.31.1](#DepthAI%202.31.1)
 * [DepthAI 2.31.0](#DepthAI%202.31.0)
 * [DepthAI 2.30.0](#DepthAI%202.30.0)
 * [DepthAI 2.29.0](#DepthAI%202.29.0)
 * [DepthAI 2.28.0](#DepthAI%202.28.0)
 * [DepthAI 2.27.0](#DepthAI%202.27.0)
 * [DepthAI 2.26.0](#DepthAI%202.26.0)

### DepthAI 2.32.0

Features:

 * Add a `device.getState` function, which returns the firmware state of the device in runtime
 * Add `setProcessor` function to select the processor for Sync and Demux nodes

Misc:

 * Expand crashdump data in firmware with more context on what caused the crash

### DepthAI 2.31.1

Released January 23, 2026

Bug fixes

 * Fix a hard to hit cache coherency bug in `MessageGroup` message
 * Remove fixed pattern noise for the OV9[2/7]82 sensor during bright scenes with low exposure times

### DepthAI 2.31.0

Released November 28, 2025

Features

 * Add tuning for the IMX577 sensor, removing the previously present blue tint
 * Improve IMX678 support on RVC2 with better black level correction, improving brightness and color accuracy New devices support
 * Add support for a new revision of OAK-Thermal (R8)
 * Add support for OAK-ToF (R4)
 * Add support for a new revision of OAK-D-S2-[Pro]-Wide OV9728 variant (R8) Bug fixes and stability
 * Fix a rare issue of IMU preventing a device reboot
 * Fix a timestamp overflow bug on the BNO08x IMU
 * Fix an edge case where `dai.Device` constructor could get stuck indefinitely if the device lost connection at the wrong time by
   adding a timeout internally
 * Turn on the watchdog early during discovery of RVC2 USB devices to avoid soft bricking the device along with handling the case
   where the device gets into that state to recover it on the next boot
 * Fully disable crashdump extraction when `DEPTHAI_CRASHDUMP=0` is set Misc
 * Add support to explicitly remove tracklets in `ObjectTracker` node
 * Remove limitation for the maximum watchdog frequency from 4.5 seconds to unlimited ("infinity") by adding a software watchdog
   in firmware

### DepthAI 2.30

Released March 18, 2025

Features

 * Add OAK4/RVC4 discovery, will throw a warning that user should use DepthAI v3
 * Add support for new VCM enabling auto-focus on new IMX378 CCMs Bug fixes
 * Fix edge case in [ImageManip](https://docs.luxonis.com/software/depthai-components/nodes/image_manip.md) to fix
   [geaxgx/depthai_hand_tracker](https://github.com/geaxgx/depthai_hand_tracker) run in edge mode
 * Fix edge case when sending [MessageGroup](https://docs.luxonis.com/software/depthai-components/messages/message_group.md) from
   host to device when sending more than 4 messages
 * Fix a bug where standalone logging would cause a memory leak

### DepthAI 2.29

Released November 25, 2024

Features

 * Add the ability to change the calibration on the device in runtime with the new `dai::Device.setCalibration()` method and to
   retrieve it with the `dai::Device.getCalibration()`.
 * New `StereoDepth` presets:
    * `DEFAULT`
    * `FACE`
    * `HIGH_DETAIL`
    * `ROBOTICS`
 * Multiple camera improvements (more details in
   [https://github.com/luxonis/depthai-core/pull/972](https://github.com/luxonis/depthai-core/pull/972)):
    * Expose more downsampling modes when picking a lower than native resolutions
    * Expose more binning modes when binning is picked on IMX582/586 (`sum` and `avg`)
    * HDR on IMX582/586
    * Option to bypass 3A for having manual expose/ISO take effect faster
    * Initial support for new Sony 4K Stravis sensors: IMX678 and IMX715
    * Option to set the main camera to drive auto-exposure and auto-white-balance in multi-camera configurations
 * Improved StereoDepth filtering and an option to use a set a custom order of filters
    * Disparity is first scaled to 13 bit before going through filtering, which results in filters being more effective.

Misc

 * Remove false reports on crashes that happened on device destruction
 * Add `getWidth()` and `getHeight()` API to `EncodedFrame`

### DepthAI 2.28.0

Released August 20, 2024

Features

 * Changed the automatic crashdump collection to always on unless `DEPTHAI_DISABLE_CRASHDUMP_COLLECTION` is set.
 * Added `DEPTHAI_ENABLE_ANALYTICS_COLLECTION` environment variable - when set, analytic data (pipeline schema only) is sent to
   Luxonis which will be used to further improve the library.
 * Undistort both outputs of ToF by default.
 * Improved 3A syncing on OAK-D-LR.
 * Added support for YoloV10.

Bug Fixes

 * Fix `Camera` node to correctly allocate resources for undistortion.
 * Fix `StereoDepth` node when decimation filter and depth alignment are used.
 * Fix host timestamps on OAK-T to be synced correctly.

Misc

 * Updated XLink to support clangd and shared libraries on Windows.
 * Removed a custom assert to always produce a crash dump to improve the UX with the automatic crashdump collection.
 * Increased watchdog priority on device side to improve stability during high load.

### DepthAI 2.27.0

Released June 27, 2024

Features

 * Automatic crash dump collection when `DEPTHAI_ENABLE_FEEDBACK_CRASHDUMP` is set

Fixes and stability improvements

 * Fix `PointCloud` generation when depth comes out of the `ImageAlign` node
 * Fix IMX214 (OAK Lite) potential crash on init with more complex pipelines
 * Fix a rare bug on a crash if a camera stream is closed after 1 second while AF is running

Python only

 * Add support for numpy 2

### DepthAI 2.26.0

Released: May 26, 2024

Features

 * ImageAlign node
    * it can align depth to any other sensor on the device - works for ToF too.
    * it can align two sensors with a static depth (default at infinity), useful for thermal-rgb alignment
 * Cast node
    * Casts `NNData` message to `ImgFrame`
    * Useful in case apps need to use outputs from `NeuralNetwork` node to be fed into nodes that only accept `ImgFrame`
 * Full ToF support
    * Running live at 30 FPS
    * Measuring range of 20cm - 6m
    * < 1% error across the range
 * Support for ToF in spatial nodes
 * An option to limit bandwidth over `XLink setXLinkRateLimit(int maxRateBytesPerSecond, int burstSize, int delayUs)`

Fixes and stability improvements

 * Improved PoE stability on reboots - eliminate a case where power cycle of the device was sometimes needed
 * Improved runtime stability of heavy pipelines by increasing priority of the cameras in the NoC
 * Improved ImageManip stability
 * Improved XLink communication to be able to detect memory corruption and avoid it
 * Fix a bug where stereo rectification was inaccurate when the calibration data didn't contain direct link between the two inputs
   * Relevant for custom setups on FFC devices

Misc

 * Improve numerical stability of the rectification algorithm * Improves stereo quality on wide FOV sensors

Python only

 * Add docs strings to stubs - docs are shown in vscode by default now
 * Fix stubs/autocomplete to correctly work with with `dai.Device() as device`
 * Fix stubs/autocomplete to return the correct type in `getCvFrame` function.