Properties for the AR SDK Features

This section provides the properties and their values for the features in the AR SDK.

Face Tracking Property Values

The following tables list the values for the configuration, input, and output properties for face tracking.

Table 3‑1: Configuration Properties for Face Tracking

Property Name	Value
FeatureDescription	String is free-form text that describes the feature. The string is set by the SDK and cannot be modified by the user.
CUDAStream	The CUDA stream, which is set by the user.
ModelDir	String that contains the path to the folder that contains the TensorRT package files. Set by the user.
ModelCacheDir	(Windows on Arm only, such as RTX Spark) Optional string path to the model runtime cache directory. Empty or unset selects ModelDir/cache. Set by the user before NvAR_Load().
ModelCacheMode	(Windows on Arm only, such as RTX Spark) Optional unsigned integer that controls the model runtime cache: 0 = Auto (default), 1 = Disabled, 2 = ForceRegenerate. Set by the user before NvAR_Load().
Temporal	Unsigned integer to enable (1) or disable (0) the temporal optimization of face detection. If enabled, only one face is returned. For more information, refer to Face Detection and Tracking. Set by the user.

Table 3‑2: Input Properties for Face Tracking

Property Name	Value
Image	Interleaved (or chunky) 8-bit BGR input image in a CUDA buffer of type NvCVImage. To be allocated and set by the user.

Table 3‑3: Output Properties for Face Tracking

Property Name	Value
BoundingBoxes	NvAR_BBoxes structure that holds the detected face boxes. To be allocated by the user.
BoundingBoxesConfidence	Optional: An array of single-precision (32-bit) floating-point numbers that contain the confidence values for each detected face box. To be allocated by the user.

Landmark Tracking Property Values

The following tables list the values for the configuration, input, and output properties for landmark tracking.

Table 3‑4: Configuration Properties for Landmark Tracking

Property Name	Value
FeatureDescription	String that describes the feature.
CUDAStream	The CUDA stream. Set by the user.
ModelDir	String that contains the path to the folder that contains the TensorRT package files. Set by the user.
ModelCacheDir	(Windows on Arm only, such as RTX Spark) Optional string path to the model runtime cache directory. Empty or unset selects ModelDir/cache. Set by the user before NvAR_Load().
ModelCacheMode	(Windows on Arm only, such as RTX Spark) Optional unsigned integer that controls the model runtime cache: 0 = Auto (default), 1 = Disabled, 2 = ForceRegenerate. Set by the user before NvAR_Load().
BatchSize	The number of inferences to be run at one time on the GPU. The maximum value is 8. Temporal optimization of landmark detection is supported only for BatchSize=1.
Landmarks_Size	Unsigned integer, 68 or 126. Specifies the number of landmark points (x and y values) to be returned. Set by the user.
LandmarksConfidence_Size	Unsigned integer, 68 or 126. Specifies the number of landmark confidence values for the detected keypoints to be returned. Set by the user.
Temporal	Unsigned integer to enable (1) or disable (0) the temporal optimization of landmark detection. If enabled, only one input bounding box is supported as the input. For more information, refer to Face Detection and Tracking. Set by the user.
Mode	Optional: Unsigned integer. Set 0 to enable Performance mode (default) or 1 to enable Quality mode for landmark detection. Set by the user.

Table 3‑5: Input Properties for Landmark Tracking

Property Name	Value
Image	Interleaved (or chunky) 8-bit BGR input image in a CUDA buffer of type NvCVImage. To be allocated and set by the user.
BoundingBoxes	Optional: NvAR_BBoxes structure that contains the number of bounding boxes that are equal to BatchSize on which to run landmark detection. If not specified as an input property, face detection is automatically run on the input image. For more information, refer to Face Detection and Tracking. To be allocated by the user.

Table 3‑6: Output Properties for Landmark Tracking

Property Name	Value
Landmarks	NvAR_Point2f array, which must be large enough to hold the number of points given by the product of NvAR_Parameter_Config(BatchSize) and NvAR_Parameter_Config(Landmarks_Size). To be allocated by the user.
Pose	Optional: NvAR_Quaternion array, which must be large enough to hold the number of quaternions equal to NvAR_Parameter_Config(BatchSize). The OpenGL standards coordinate convention is used: When you look up from a camera, the coordinates are x (camera right), y (camera up), and z (toward camera). To be allocated by the user.
LandmarksConfidence	Optional: An array of single-precision (32-bit) floating-point numbers, which must be large enough to hold the number of confidence values given by the product of the following: NvAR_Parameter_Config(BatchSize) NvAR_Parameter_Config(LandmarksConfidence_Size) To be allocated by the user.
BoundingBoxes	Optional: NvAR_BBoxes structure that contains the detected face through face detection performed by the landmark detection feature. For more information, refer to Face Detection and Tracking. To be allocated by the user.

Eye Contact Property Values

The following tables list the values for the configuration, input, and output properties for gaze redirection.

Table 3‑7: Configuration Properties for Eye Contact

Property Name	Value
FeatureDescription	String that describes the feature.
ModelDir	String that contains the path to the folder that contains the TensorRT package files. Set by the user.
ModelCacheDir	(Windows on Arm only, such as RTX Spark) Optional string path to the model runtime cache directory. Empty or unset selects ModelDir/cache. Set by the user before NvAR_Load().
ModelCacheMode	(Windows on Arm only, such as RTX Spark) Optional unsigned integer that controls the model runtime cache: 0 = Auto (default), 1 = Disabled, 2 = ForceRegenerate. Set by the user before NvAR_Load().
BatchSize	The number of inferences to be run at one time on the GPU. The maximum value is 1.
Landmarks_Size	Unsigned integer, either 68 or 126. Specifies the number of landmark points (x and y values) to be returned. Set by the user.
LandmarksConfidence_Size	Unsigned integer, either 68 or 126. Specifies the number of landmark confidence values for the detected keypoints to be returned. Set by the user.
GazeRedirect	Flag to enable or disable gaze redirection. When enabled, the gaze is estimated, and the redirected image is set as the output. When disabled, the gaze is estimated but redirection does not occur.
Temporal	Unsigned integer to enable (1) or disable (0) the temporal optimization of landmark detection. Set by the user.
DetectClosure	Flag to toggle the detection of eye closure and occlusion. The default value is On.
EyeSizeSensitivity	An unsigned integer in the range 2–5, inclusive, that is used to increase the sensitivity of the algorithm to the redirected eye size. A value of 2 uses a smaller eye region, and a value of 5 uses a larger eye size.
UseCudaGraph	Bool. Default is False. Flag to use CUDA Graphs for optimization. Recommended on Windows on Arm (for example, RTX Spark) for better steady-state performance. Set by the user.
EnableLookAway	Bool. Default is false. Flag that, when set to true, redirects the eyes to look away at a random time for a random period. The eyes follow the relative changes in estimated gaze during the lookaway period. Set by the user.
LookAwayOffsetMax	Unsigned int value in the range 0–10. Default is 5. If the value is set to x degrees, a randomly chosen offset angle in the range −*x* to x in degrees will be added to the lookaway angle during the random lookaway period. The lookaway angle is based on the relative motion of the eyes in the input image during the lookaway period. It is not used outside the lookaway period. Set by the user.
LookAwayIntervalMin	Unsigned int value in the range 1–600. Default is 100. Minimum limit for the number of frames at which random look away occurs. This value is applicable only when EnableLookAway is set to true. The value can be optionally set by the user.
LookAwayIntervalRange	Unsigned int value in the range 1–600. Default is 250. Interval range for picking the number of frames at which random lookaway occurs. Adding this range to LookAwayIntervalMin provides the maximum limit for the number of frames at which random lookaway occurs. This value is applicable only when EnableLookAway is set to true. The value can be optionally set by the user.
GazePitchThresholdLow	Float value in the range of 10.0–35.0 (degrees). Default is 20.0. This is a range control parameter. It defines the threshold for estimated gaze angle in the pitch direction within which gaze is always redirected towards the camera. Beyond this angle, the redirected gaze transitions away from the camera and towards the estimated gaze angle. This value is optionally set by the user.
GazeYawThresholdLow	Float value in the range of 10.0–35.0 (degrees). Default is 20.0. This is a range control parameter. It defines the threshold for estimated gaze angle in the yaw direction within which gaze is always redirected towards the camera. Beyond this angle, the redirected gaze transitions away from the camera and towards the estimated gaze angle. This value is optionally set by the user.
HeadPitchThresholdLow	Float value in the range of 10.0–35.0 (degrees). Default is 15.0. This is a range control parameter. It defines the threshold for estimated head pose angle in the pitch direction within which gaze is always redirected towards the camera. Beyond this angle, the redirected gaze transitions away from the camera and towards the estimated gaze angle. This value is optionally set by the user.
HeadYawThresholdLow	Float value in the range of 10.0–35.0 (degrees). Default is 25.0. This is a range control parameter. It defines the threshold for estimated head pose angle in the yaw direction within which gaze is always redirected towards the camera. Beyond this angle, the redirected gaze transitions away from the camera and towards the estimated gaze angle. This value is optionally set by the user.
GazePitchThresholdHigh	Float value in the range of 10.0–35.0 (degrees). Default is 30.0. This is a range control parameter. It defines the threshold for estimated gaze angle in the pitch direction beyond which no redirection occurs and the angle of redirected gaze is equal to the estimated gaze. The redirected gaze in the pitch direction increasingly moves away from the camera and towards the estimated gaze beyond GazePitchThresholdLow and reaches the estimated gaze value at GazePitchThresholdHigh. The value of this parameter is expected to be greater than GazePitchThresholdLow. This value is optionally set by the user.
GazeYawThresholdHigh	Float value in the range of 10.0–35.0 (degrees). Default is 30.0. This is a range control parameter. It defines the threshold for estimated gaze angle in the yaw direction beyond which no redirection occurs and the angle of redirected gaze is equal to the estimated gaze. The redirected gaze in the yaw direction increasingly moves away from the camera and towards the estimated gaze beyond GazeYawThresholdLow and reaches the estimated gaze value at GazeYawThresholdHigh. The value of this parameter is expected to be greater than GazeYawThresholdLow. This value is optionally set by the user.
HeadPitchThresholdHigh	Float value in the range of 10.0-35.0 (degrees). Default value 25.0. This is a range control parameter. It defines the threshold for estimated head pose angle in the pitch direction beyond which no redirection occurs and the angle of redirected gaze is equal to the estimated gaze. The redirected gaze in the pitch direction increasingly moves away from the camera and towards the estimated gaze beyond HeadPitchThresholdLow and reaches the estimated gaze value at HeadPitchThresholdHigh. The value of this parameter is expected to be greater than HeadPitchThresholdLow. This value is optionally set by the user.
HeadYawThresholdHigh	Float value in the range of 10.0-35.0 (degrees). Default value 30.0. This is a range control parameter. It defines the threshold for estimated head pose angle in the yaw direction beyond which no redirection occurs and the angle of redirected gaze is equal to the estimated gaze. The redirected gaze in the yaw direction increasingly moves away from the camera and towards the estimated gaze beyond HeadYawThresholdLow and reaches the estimated gaze value at HeadYawThresholdHigh. The value of this parameter is expected to be greater than HeadYawThresholdLow. This value is optionally set by the user.
MultiPerson	Unsigned int value of 0 or 1. Default is 0. Set to 1 to redirect the gaze of every detected face, up to eight faces per video stream. Set to 0 to redirect the gaze of a single face. This value is optionally set by the user.

Table 3‑8: Input Properties for Eye Contact

Property Name	Value
Image	Interleaved (or chunky) 8-bit BGR input image in a CUDA buffer of type NvCVImage. To be allocated and set by the user.
Width	The width of the input image buffer that contains the face to which the face model will be fitted. Set by the user.
Height	The height of the input image buffer that contains the face to which the face model will be fitted. Set by the user.
Landmarks	Optional: An NvAR_Point2f array that contains the landmark points of size NvAR_Parameter_Config(Landmarks_Size) that is returned by the landmark detection feature. If landmarks are not provided to this feature, an input image must be provided. To be allocated by the user.

Table 3‑9: Output Properties for Eye Contact

Property Name	Value
Landmarks	NvAR_Point2f array, which must be large enough to hold the number of points given by the product of the following: NvAR_Parameter_Config(BatchSize) NvAR_Parameter_Config(Landmarks_Size) To be allocated by the user.
HeadPose	Optional: NvAR_Quaternion array, which must be large enough to hold the number of quaternions equal to NvAR_Parameter_Config(BatchSize). The OpenGL standards coordinate convention is used: When you look up from a camera, the coordinates are x (camera right), y (camera up), and z (toward the camera). To be allocated by the user.
LandmarksConfidence	Optional: An array of single-precision (32-bit) floating-point numbers, which must be large enough to hold the number of confidence values given by the product of the following: NvAR_Parameter_Config(BatchSize) NvAR_Parameter_Config(LandmarksConfidence_Size) To be allocated by the user.
BoundingBoxes	Optional: NvAR_BBoxes structure that contains the detected face through face detection performed by the landmark detection feature. To be allocated by the user.
OutputGazeVector	Float array, which must be large enough to hold the two values (pitch and yaw) for the gaze angle in radians per image. For batch sizes larger than 1, it should hold NvAR_Parameter_Config(BatchSize) × 2 float values. To be allocated by the user.
OutputHeadTranslation	Optional: Float array, which must be large enough to hold the head translations (x,y,z) per image. For batch sizes larger than 1, it should hold NvAR_Parameter_Config(BatchSize) × 3 float values. To be allocated by the user.
GazeDirection	Optional: NvAR_Point3f array that is large enough to hold as many elements as NvAR_Parameter_Config(BatchSize). Each element contains two NvAR_Point3f points. One point represents the center point (cx,cy,cz) between the eyes, and the other point represents a unit vector (ux, uy, uz) in the gaze direction for visualization. For batch sizes larger than 1, it should hold NvAR_Parameter_Config(BatchSize) × 2 NvAR_Point3f points. To be allocated by the user.

Body Detection Property Values

The following tables list the configuration, input, and output property values for Body Detection.

Table 3‑10: Configuration Properties for Body Detection

Property Name	Value
FeatureDescription	String is free-form text that describes the feature. The string is set by the SDK and cannot be modified by the user.
CUDAStream	The CUDA stream, which is set by the user.
ModelDir	String that contains the path to the folder that contains the TensorRT package files. Set by the user.
ModelCacheDir	(Windows on Arm only, such as RTX Spark) Optional string path to the model runtime cache directory. Empty or unset selects ModelDir/cache. Set by the user before NvAR_Load().
ModelCacheMode	(Windows on Arm only, such as RTX Spark) Optional unsigned integer that controls the model runtime cache: 0 = Auto (default), 1 = Disabled, 2 = ForceRegenerate. Set by the user before NvAR_Load().
Temporal	Unsigned integer to enable (1) or disable (0) the temporal optimization of body detection. Set by the user.
FullBodyOnly	Unsigned integer to select the estimation mode: 1: Full Body only (default). 0: Full and upper body. Set by the user.

Table 3‑11: Input Properties for Body Detection

Property Name	Value
Image	Interleaved (or chunky) 8-bit BGR input image in a CUDA buffer of type NvCVImage. To be allocated and set by the user.

Table 3‑12: Output Properties for Body Detection

Property Name	Value
BoundingBoxes	NvAR_BBoxes structure that holds the detected body boxes. To be allocated by the user.
BoundingBoxesConfidence	Optional: An array of single-precision (32-bit) floating-point numbers that contain the confidence values for each detected body box. To be allocated by the user.

Legacy 3D Body Pose Keypoint Tracking Property Values

The following tables list the configuration, input, and output property values for the legacy 3D Body Pose Keypoint Tracking feature.

Table 3‑13: Configuration Properties for Legacy 3D Body Pose Keypoint Tracking

Property Name	Value
FeatureDescription	String that describes the feature.
CUDAStream	The CUDA stream. Set by the user.
ModelDir	String that contains the path to the folder that contains the TensorRT package files. Set by the user.
BatchSize	The number of inferences to be run at one time on the GPU. The maximum value is 1.
Mode	Unsigned integer that specifies the mode: High Performance (1) or High Quality (0). Default is 1. Set by the user.
UseCudaGraph	Boolean to enable (true) or disable (false) the use of CUDA Graphs for optimization. Set by the user.
Temporal	Unsigned integer to enable (1) or disable (0) the temporal optimization of Body Pose tracking. Set by the user.
NumKeyPoints	Unsigned integer that specifies the number of keypoints available, which is currently 34.
ReferencePose	NvAR_Point3f array that contains the reference pose for each of the keypoints. Set by the user.
FullBodyOnly	Unsigned integer to select the pose estimation mode: Full Body only (1). Supports both high quality and high performance modes. Full and upper body (0). Supports only high quality mode. The default is 1. Set by the user.
PostprocessJointAngle	Boolean to enable (true) or disable (false) the postprocessing steps for joint angles corresponding to the joints predicted with low confidence. To be used only when FullBodyOnly is set to 0. We recommend that you set this to true when input is upper-body image or video. The default is true. Set by the user.
TargetSeatedPoseForInterpolation	NvAR_Quaternion array that contains the target seated pose (for each of the 34 keypoints) to be used for post processing joint rotations. For the joints that are predicted with low confidence, the output pose will be interpolated to the corresponding pose specified in this target pose. This array is used when the SDK detects that the person in the input frame is in a seated pose. Used only when FullBodyOnly is set to 0.
TargetStandPoseForInterpolation	NvAR_Quaternion array that contains the target standing pose (for each of the 34 keypoints) to be used for post processing joint rotations. For the joints that are predicted with low confidence, the output pose will be interpolated to the corresponding pose specified in this target pose. This array is used when the SDK detects that the person in the input frame is in a standing pose. Used only when FullBodyOnly is set to 0.
TrackPeople	Unsigned integer to enable (1) or disable (0) multi-person tracking in Body Pose. Set by the user.
ShadowTrackingAge	Unsigned integer that specifies the age (in number of frames) after which the multi-person tracker stops tracking the object in shadow mode. The default is 90. Set by the user.
ProbationAge	Unsigned integer that specifies the age (in number of frames) after which the multi-person tracker marks the object valid and assigns an ID for tracking. The default is 10. Set by the user.
MaxTargetsTracked	Unsigned integer that specifies the maximum number of targets to be tracked by the multi-person tracker. After the tracking is complete, the new targets are discarded. The default is 30. Set by the user.

Table 3‑14: Input Properties for Legacy 3D Body Pose Keypoint Tracking

Property Name	Value
Image	Interleaved (or chunky) 8-bit BGR input image in a CUDA buffer of type NvCVImage. To be allocated and set by the user.
FocalLength	Float value that specifies the focal length of the camera to be used for 3D Body Pose. The default value is 800.79041. To be allocated and set by the user.
BoundingBoxes	Optional: NvAR_BBoxes structure that contains the number of bounding boxes that are equal to BatchSize on which to run 3D Body Pose detection. If not specified as an input property, body detection is automatically run on the input image. To be allocated by the user.

Table 3‑15: Output Properties for Legacy 3D Body Pose Keypoint Tracking

Property Name	Value
Keypoints	NvAR_Point2f array, which must be large enough to hold the points given by the product of NvAR_Parameter_Config(BatchSize) and 34. To be allocated by the user.
Keypoints3D	NvAR_Point3f array, which must be large enough to hold the points given by the product of NvAR_Parameter_Config(BatchSize) and 34. To be allocated by the user.
JointAngles	NvAR_Quaternion array, which must be large enough to hold the joints given by the product of NvAR_Parameter_Config(BatchSize) and 34. Each value represents the local rotation of one joint relative to ReferencePose. To be allocated by the user.
KeyPointsConfidence	An array of single-precision (32-bit) floating-point numbers, which must be large enough to hold the number of confidence values given by the product of NvAR_Parameter_Config(BatchSize) and 34. To be allocated by the user.
BoundingBoxes	NvAR_BBoxes structure that contains the detected body through body detection performed by the 3D Body Pose feature. To be allocated by the user.
TrackingBoundingBoxes	NvAR_TrackingBBoxes structure that contains the detected body through body detection that is completed by the 3D Body Pose feature and the tracking ID assigned by multi-person tracking. To be allocated by the user.

3D Body Pose Estimation Property Values

The following tables list the configuration, input, and output properties for 3D Body Pose Estimation.

Configuration Properties for 3D Body Pose Estimation

Property Name	Value
FeatureDescription	String that describes the feature.
CUDAStream	CUDA stream used to run the feature. Set before NvAR_Load.
ModelDir	Path to the folder that contains the TensorRT package files. Set before NvAR_Load.
Mode	Unsigned integer mode selector. NVAR_3DBODYPOSE_MODE_2D is 0 and NVAR_3DBODYPOSE_MODE_3D is 1. The default is NVAR_3DBODYPOSE_MODE_3D.
MaxBoxesPerFrame	Read-only unsigned integer that reports the maximum number of tracked bodies that are accepted per frame.
NumKeyPoints	Read-only unsigned integer that reports the number of public keypoints per body. The current value is 77.
EnableContact	Unsigned integer that enables contact correction and contact-driven inverse kinematics (IK) in 3D mode. 0 disables it and 1 enables it. The default is 1. Set this property before NvAR_Load. Keep it enabled for fixed-camera scenes and whenever contact stability matters. Disable it when the camera moves, or when lower compute cost matters more than contact stabilization, because disabling it can increase visible drift and sliding.

Input Properties for 3D Body Pose Estimation

Property Name	Value
Image	Interleaved or chunky 8-bit BGR input image in a CUDA buffer of type NvCVImage. Required for normal frame processing.
TrackingBoundingBoxes	NvAR_TrackingBBoxes structure that contains caller-provided tracked body boxes and tracking IDs for the current frame.
FocalLength	Optional focal length in pixels. If this property is unset or set to 0, the feature derives a focal length from the input image size.
Flush	Unsigned integer stream-drain control. 0 is normal processing, and 1 flushes delayed outputs at the end of the stream.

Output Properties for 3D Body Pose Estimation

Property Name	Value
Ready	Read-only unsigned integer. 1 means that an output frame is available and that the registered output buffers contain valid data.
StreamFlushed	Read-only unsigned integer. 1 means that end-of-stream flushing is complete for the bound stream.
NumBodies	Read-only unsigned integer that reports the number of valid output bodies in the output frame that is ready.
TrackingBoundingBoxes	NvAR_TrackingBBoxes structure that receives the output-frame body boxes and tracking IDs.
KeyPoints	NvAR_Point2f array of 2D keypoints. Allocate at least MaxBoxesPerFrame * NumKeyPoints elements.
KeyPointsConfidence	Single-precision confidence array. Allocate at least MaxBoxesPerFrame * NumKeyPoints elements.
KeyPoints3D	NvAR_Point3f array of posed 3D keypoints in camera coordinates, in meters. Allocate at least MaxBoxesPerFrame * NumKeyPoints elements.
RestPose	NvAR_Point3f array of root-relative rest-pose keypoints in the SDK direct-rest basis, in meters. Allocate at least MaxBoxesPerFrame * NumKeyPoints elements.
RootPose	NvAR_Transform3f array of root pose values. Translation is in camera coordinates, in meters; rotation maps root-relative direct-rest points into the camera coordinate system. Allocate at least MaxBoxesPerFrame elements.
JointRotations	NvAR_Quaternion array of local joint rotations in SDK skeleton order and in the SDK direct-rest basis. Allocate at least MaxBoxesPerFrame * NumKeyPoints elements.
JointAngles	Compatibility alias for JointRotations.

Facial Expression Estimation Property Values

The following tables list the values for the configuration, input, and output properties for Facial Expression Estimation.

Table 3‑16: Configuration Properties for Facial Expression Estimation

Property Name	Value
FeatureDescription	String that describes the feature. This property is read-only.
ModelDir	String that contains the path to the face model and the TensorRT package files. Set by the user.
ModelCacheDir	(Windows on Arm only, such as RTX Spark) Optional string path to the model runtime cache directory. Empty or unset selects ModelDir/cache. Set by the user before NvAR_Load().
ModelCacheMode	(Windows on Arm only, such as RTX Spark) Optional unsigned integer that controls the model runtime cache: 0 = Auto (default), 1 = Disabled, 2 = ForceRegenerate. Set by the user before NvAR_Load().
CUDAStream	Optional: The CUDA stream. Set by the user.
Temporal	Optional: Bitfield to control temporal filtering. 0x001: Filter face detection. 0x002: Filter facial landmarks. 0x004: Filter rotational pose. 0x010: Filter facial expressions. 0x020: Filter gaze expressions. 0x100: Enhance eye and mouth closure. Default is 0x037 (all on except 0x100). Set by the user.
Landmarks_Size	Unsigned integer, 68 or 126. Required array size of detected facial landmark points. Length of array must be 126, to accommodate {x,y} location of each of the detected points.
ExpressionCount	Unsigned integer. The number of expressions in the face model.
PoseMode	Specifies how to compute pose. 0 = 3DOF (default), 1 = 6DOF explicit. 6DOF is required for 3D translation output.
Mode	Flag to toggle landmark mode. Set 0 to enable Performance model for landmark detection. Set 1 to enable Quality model for landmark detection for higher accuracy. Default is 1.
EnableCheekPuff	(Experimental) Enables cheek puff blendshapes.

Table 3‑17: Input Properties for Facial Expression Estimation

Property Name	Value
Landmarks	Optional: An NvAR_Point2f array that contains the landmark points of size NvAR_Parameter_Config(Landmarks_Size) that is returned by the landmark detection feature. If landmarks are not provided to this feature, an input image must be provided. To be allocated by the user.
Image	Optional: An interleaved (or chunky) 8-bit BGR input image in a CUDA buffer of type NvCVImage. If an input image is not provided as input, the landmark points must be provided to this feature as input. To be allocated by the user.
CameraIntrinsicParams	Optional: Camera intrinsic parameters. A three-element float array with elements corresponding to focal length, cx, and cy, respectively, of an ideal perspective camera. Any barrel or fisheye distortion should be removed or considered negligible. Used only if PoseMode is set to 1.

Table 3‑18: Output Properties for Facial Expression Estimation

Property Name	Value
Landmarks	Optional: An NvAR_Point2f array, which must be large enough to hold the number of points of size NvAR_Parameter_Config(Landmarks_Size).
Pose	Optional: NvAR_Quaternion Pose rotation quaternion. Coordinate frame is NvAR Camera 3D pace. To be allocated by the user.
PoseTranslation	Optional: NvAR_Point3f Pose 3D Translation. Computed only if PoseMode = 1. Translation coordinates are in NvAR Camera 3D Space coordinates, in which the units are centimeters. To be allocated by the user.
LandmarksConfidence	Optional: An array of single-precision (32-bit) floating-point numbers, which must be large enough to hold the number of confidence values of size NvAR_Parameter_Config(LandmarksConfidence_Size). To be allocated by the user.
BoundingBoxes	Optional: NvAR_BBoxes structure that contains the detected face that is determined internally. To be allocated by the user.
BoundingBoxesConfidence	Optional: An array of single-precision (32-bit) floating-point numbers, which must be large enough to hold the number of confidence values of size NvAR_Parameter_Config(BoundingBoxesConfidence_Size). To be allocated by the user.
ExpressionCoefficients	The array into which the expression coefficients will be placed, if desired. Query ExpressionCount to determine the size for this array. To be allocated by the user. The corresponding expression shapes are in the following order: BrowDown_L, BrowDown_R, BrowInnerUp_L, BrowInnerUp_R, BrowOuterUp_L, BrowOuterUp_R, CheekPuff_L, CheekPuff_R, CheekSquint_L, CheekSquint_R, EyeBlink_L, EyeBlink_R, EyeLookDown_L, EyeLookDown_R, EyeLookIn_L, EyeLookIn_R, EyeLookOut_L, EyeLookOut_R, EyeLookUp_L, EyeLookUp_R, EyeSquint_L, EyeSquint_R, EyeWide_L, EyeWide_R, JawForward, JawLeft, JawOpen, JawRight, MouthClose, MouthDimple_L, MouthDimple_R, MouthFrown_L, MouthFrown_R, MouthFunnel, MouthLeft, MouthLowerDown_L, MouthLowerDown_R, MouthPress_L, MouthPress_R, MouthPucker, MouthRight, MouthRollLower, MouthRollUpper, MouthShrugLower, MouthShrugUpper, MouthSmile_L, MouthSmile_R, MouthStretch_L, MouthStretch_R, MouthUpperUp_L, MouthUpperUp_R, NoseSneer_L, NoseSneer_R

LipSync Property Values

The following tables list the values for the configuration, input, and output properties for LipSync.

Table 3‑19: Configuration Properties for LipSync

Property Name	Value
FeatureDescription	String that describes the feature. This property is read-only.
ModelDir	String that contains the path to the face model and the TensorRT package files. Set by the user.
Language	Unsigned 32-bit value that selects which language-specific LipSync TensorRT model is loaded from ModelDir. 0: Generic (default). 1: German (lipsync_DE variant). 2: French (lipsync_FR variant). 3: Spanish (lipsync_ES variant). Set this parameter before calling NvAR_Load. The deployment must include the matching model package for the selected language. Set by the user.
CUDAStream	Optional: The CUDA stream. Set by the user.
VideoFPS	The video frame rate in frames per second. Set by the user.
SampleRate	The sample rate for the audio input. The feature supports 16-kHz audio only. This property is read-only.
NumChannels	The number of channels for the audio input. The feature supports mono channel audio only. This property is read-only.
NumInitialFrames	The number of initial audio frames before the first image can be generated. You need to provide NumInitialFrames number of video frames before the first output is available at Image output. The default value is 14. This property is read-only.

Table 3‑20: Input Properties for LipSync

Property Name	Value
Image	Chunky/packed CUDA buffer. Supported formats: BGR-U8, BGR-U16, BGRA-U16, RGBA-U16. The component type (U8 or U16) must match between the input and output images. Requirements: Resolution between 360p and 4K. Face region in the input frame up to 512×512 resolution. The full face of the subject is visible. Maximum of ±30 degrees head movement in each axis. Moderate to good lighting conditions. Clear face features; no occlusion.
AudioFrameBuffer	Raw audio frame buffer in CPU ranging from –1.0 to 1.0, inclusive. When the LipSync feature is run, it assumes that the contents of the audio frame buffer are synchronized with the current input video frame. The length of the audio frame should approximately match the duration of the video frame. The caller can vary the length of each audio frame to maintain synchronization. Audio requirements: Sample rate: 16 kHz. Channel: 1 (mono). Only one person speaking at a time. No background noise.
LipSyncRegionData	Optional: An NvAR_LipSyncRegionData object that specifies the regions and per-region settings for LipSync, including tracking ID, bypass, region type, and speaking flag. When not set (nullptr), the feature operates in single full-frame region mode. Attention SpeakerData is no longer supported. Use LipSyncRegionData instead.
HeadMovementSpeed	Optional: Speed of head movement in the input video. 0: Static/slow-moving head. 1: Fast-moving head. Default: 0. Set by the user.

Table 3‑21: Output Properties for LipSync

Property Name	Value
Image	Chunky/packed CUDA buffer. Supported formats: BGR-U8, BGR-U16, BGRA-U16, RGBA-U16. The component type must match the input image.
Ready	Flag that is set to a non-zero value when the first output video frame is generated.
Activation	An NvAR_LipSyncActivation structure that provides the activation strength and the location and size of the animated face. The strength field is a value in the range 0–1 that indicates the activation level. When 0, the original face was copied directly to the output without modification. When 1, the original face was completely replaced by the animated face. The center_x, center_y, and size fields provide the face center location and size in pixels.

Active Speaker Detection Property Values

The following tables list the values for the configuration, input, and output properties for Active Speaker Detection.

Table 3‑22: Configuration Properties for Active Speaker Detection

Property Name	Value
FeatureDescription	String that describes the feature. This property is read-only.
ModelDir	String that contains the path to the TensorRT model files. Set by the user.
CUDAStream	Optional: The CUDA stream. Set by the user.
VideoFPS	Video frames per second. Must be in the range (0.0, 120.0]. Default: 30.0.
NumAudioStreams	Number of audio tracks to process. Must be in the range [1, 30]. Default: 1.
SampleRate	Audio sample rate in Hz. Must be in the range (0, 96000]. Default: 44100.
SyncTolerance	Minimum audio-visual sync score in the range (0, 1) to consider a face as speaking. Higher values require stronger sync evidence. Set by the user.
MaxNumOutputIdentities	Maximum number of output identities that can be tracked simultaneously. This property is read-only. Default: 30.
MaxSyncFaces	Maximum number of tracked faces to evaluate with sync discrimination on each firing. 0 disables the limit. This property does not limit the output face count. It is not a hard cap on established speakers over time. Default: 0.
Flags	Flag bits for shot-change handling and active-audio filtering behavior. Set by the user.

The following Flags are allowed:

• NVARACTIVESPEAKERDETECTION_FLAG_SHOT_CHANGED: Indicates that the frame is a shot change.

• NVARACTIVESPEAKERDETECTION_FLAG_DETECT_SHOT_CHANGE: Enables automatic shot-change detection.

• NVARACTIVESPEAKERDETECTION_FLAG_FILTER_SILENT_TRACKS: Filters silent audio tracks out of the active audio list.

• NVARACTIVESPEAKERDETECTION_FLAG_ENABLE_VAD: Runs denoiser voice-activity detection on the supplied audio tracks and filters inactive tracks.

• NVARACTIVESPEAKERDETECTION_FLAG_ENABLE_VA_SMOOTHING_LOW: Enables low voice-activity smoothing.

• NVARACTIVESPEAKERDETECTION_FLAG_ENABLE_VA_SMOOTHING_HIGH: Enables high voice-activity smoothing.

NVARACTIVESPEAKERDETECTION_FLAG_ENABLE_VAD and NVARACTIVESPEAKERDETECTION_FLAG_FILTER_SILENT_TRACKS are mutually exclusive. Use at most one voice-activity smoothing flag at a time.

When no active-audio filtering flag is set, ActiveAudioIDs is treated as authoritative, such as with diarization-driven input. When denoiser VAD or silent-track filtering is enabled, ActiveAudioIDs is the candidate audio list that can be filtered by the SDK.

The NewShot input remains supported for backward compatibility. If both NewShot and Flags are set, NewShot takes precedence for shot-change behavior.

Table 3‑23: Input Properties for Active Speaker Detection

Property Name	Value
Image	Input image in GPU memory with NVCV_BGR, NVCV_U8 format. Maximum supported resolution is 4096 × 2160. Set by the user.
AudioFrameData	Input audio frame data containing audio samples for all tracks. Type: NvAR_AudioFrameData. The audio data should be synchronized with the input video frame and contain floating-point samples in the range [-1.0, 1.0]. Set by the user.
ActiveAudioIDs	Array of active audio track IDs. Type: NvAR_ActiveAudioIds. Without VAD or silent-track filtering, only listed tracks are processed. With filtering enabled, this is the candidate list that can be filtered by the SDK. Sample applications can derive this list from diarization JSON. Set by the user.
NewShot	Shot-change mode for the current stream: 0: No shot change. 1: Shot change occurred. 255: Auto-detect shot changes (default). Set by the user.
Flush	Flush mode for the current stream: 0: Normal processing. 1: Flush mode (finalize outputs). Set by the user.

Table 3‑24: Output Properties for Active Speaker Detection

Property Name	Value
ActiveSpeakerTrackingData	Output tracking data containing detected faces with speaker information. Type: NvAR_ActiveSpeakerTrackingData. Each tracked face includes the following: Bounding box coordinates. Unique tracking ID. Associated audio track ID. Detection confidence score. Speaking status flag. To be allocated by the user.
Ready	Output ready status for the current: 0: Output not ready. 1: Output ready and valid. The feature requires multiple frames to accumulate before producing valid output.