uvTo3DInCameraSpace
Using PICO's depth sensor and stereo view RGB images, estimate the 3D coordinates of 2D points on camera output.
Parameters
the 2D coordinates of points, corresponding to one left-eye camera image. The tensor must be a point2 array, (i.e., created with Tensor.Point2ArrayInitInfo) of size N. The data type must be 32-/64-bit float.
the camera timestamp of the left-eye image to which the uv is corresponding. It must be a timestamp tensor output from rectifiedVSTAccess.
the camera intrinsic matrix of the left-eye image to which the uv is corresponding. It must be a multi-dimensional tensor of 1 channel, dimensions = 3x3 and its data type should be 32-/64-bit float. You can directly use the output from rectifiedVSTAccess.
the raw left-eye camera image from rectifiedVSTAccess. It must be the output associated with the timestamp. It is used to enhance the depth sensor's output using parallax.
the raw right-eye camera image from rectifiedVSTAccess. It must be the output associated with the timestamp. It is used to enhance the depth sensor's output using parallax.
the required result from this operation, to store the estimated 3D coordinates corresponding to the 2D points in uv. It must be a point3 array, created with Tensor.Point3ArrayInitInfo of size N, where N must match that of uv, or a multi-dimensional tensor of 1 channel and dimensions = Nx3, or 3 channels and dimensions = 1xN or Nx1.
Throws
If the usage is not allowed by the SpatialML run-time Framework, or if the framework encounter internal error and cannot perform the requested behavior.