o oi @sddZddlmZddlmZddlmZddlmZddl m Z dd d Z ddddZ dddZ dS)z?Module for the projection of points in the canonical z=1 plane.) annotations)OptionalN)TensorKORNIA_CHECK_SHAPEpoints_in_camerarreturncCs.t|ddg|dddf|dddfS)aSProject one or more points from the camera frame into the canonical z=1 plane through perspective division. .. math:: \begin{bmatrix} u \\ v \\ w \end{bmatrix} = \begin{bmatrix} x \\ y \\ z \end{bmatrix} / z .. note:: This function has a precondition that the points are in front of the camera, i.e. z > 0. If this is not the case, the points will be projected to the canonical plane, but the resulting points will be behind the camera and causing numerical issues for z == 0. Args: points_in_camera: Tensor representing the points to project with shape (..., 3). Returns: Tensor representing the projected points with shape (..., 2). Example: >>> points = torch.tensor([1., 2., 3.]) >>> project_points_z1(points) tensor([0.3333, 0.6667]) *3.Nr)rr X/home/ubuntu/.local/lib/python3.10/site-packages/kornia/geometry/camera/projection_z1.pyproject_points_z1s rpoints_in_cam_canonical extensionOptional[Tensor]cCsft|ddg|durtj|jddd|j|jd}n |jddkr(|d }tj|||gdd S) aUnproject one or more points from the canonical z=1 plane into the camera frame. .. math:: \begin{bmatrix} x \\ y \\ z \end{bmatrix} = \begin{bmatrix} u \\ v \end{bmatrix} \cdot w Args: points_in_cam_canonical: Tensor representing the points to unproject with shape (..., 2). extension: Tensor representing the extension (depth) of the points to unproject with shape (..., 1). Returns: Tensor representing the unprojected points with shape (..., 3). Example: >>> points = torch.tensor([1., 2.]) >>> extension = torch.tensor([3.]) >>> unproject_points_z1(points, extension) tensor([3., 6., 3.]) r 2N))devicedtyperr).Ndim)ropsonesshaperr concatenate)rrr r runproject_points_z1<srcCs~t|ddg|d}|d}|d}d|}||}t|}tjtj||| |gddtj||| |gddgd dS) aNCompute the derivative of the x projection with respect to the x coordinate. Returns point derivative of inverse depth point projection with respect to the x coordinate. .. math:: \frac{\partial \pi}{\partial x} = \begin{bmatrix} \frac{1}{z} & 0 & -\frac{x}{z^2} \\ 0 & \frac{1}{z} & -\frac{y}{z^2} \end{bmatrix} .. note:: This function has a precondition that the points are in front of the camera, i.e. z > 0. If this is not the case, the points will be projected to the canonical plane, but the resulting points will be behind the camera and causing numerical issues for z == 0. Args: points_in_camera: Tensor representing the points to project with shape (..., 3). Returns: Tensor representing the derivative of the x projection with respect to the x coordinate with shape (..., 2, 3). Example: >>> points = torch.tensor([1., 2., 3.]) >>> dx_project_points_z1(points) tensor([[ 0.3333, 0.0000, -0.1111], [ 0.0000, 0.3333, -0.2222]]) r r ).r).r).r g?rr)rr zeros_likestack)rxyzz_invz_sqzerosr r rdx_project_points_z1_s r()rrrr)N)rrrrrr)__doc__ __future__rtypingr kornia.corecorerrkornia.core.checkrrrr(r r r rs       #