如何使牛肝菌( kornia HomographyWarper )表现得像OpenCV warpPerspective？

Question

正如标题所述，我希望使用kornia中的HomographyWarper，以便它提供与OpenCV warpPerspective相同的输出。

import cv2
import numpy as np
import torch
from kornia.geometry.transform import HomographyWarper
from kornia.geometry.conversions import normalize_pixel_coordinates

image_cv = cv2.imread("./COCO_train2014_000000000009.jpg")
image_cv = image_cv[0:256, 0:256]
image = torch.tensor(image_cv).permute(2, 0, 1)
image = image.to('cuda:0')
image_reshaped = image.type(torch.float32).view(1, *image.shape)

height, width, _ = image_cv.shape

homography_0_1 = torch.tensor([[ 7.8783e-01,  3.6705e-02,  2.5139e+02],
        [ 1.6186e-02,  1.0893e+00, -2.7614e+01],
        [-4.3304e-04,  7.6681e-04,  1.0000e+00]], device='cuda:0',
       dtype=torch.float64)
homography_0_2 = torch.tensor([[ 7.8938e-01,  3.5727e-02,  1.5221e+02],
        [ 1.8347e-02,  1.0921e+00, -2.8547e+01],
        [-4.3172e-04,  7.7596e-04,  1.0000e+00]], device='cuda:0',
       dtype=torch.float64)
transform_h1_h2 = torch.linalg.inv(homography_0_1).matmul(
                        homography_0_2).type(torch.float32).view(1, 3, 3)

homography_warper_1_2 = HomographyWarper(height, width, padding_mode='zeros', normalized_coordinates=True)
warped_image_torch = homography_warper_1_2(image_reshaped, transform_h1_h2)

warped_image_1_2_cv = cv2.warpPerspective(
                        image_cv,
                        transform_h1_h2.cpu().numpy().squeeze(),
                        dsize=(width, height),
                        borderMode=cv2.BORDER_REFLECT101,
                    )

cv2.namedWindow("original image")
cv2.imshow("original image", image_cv)
cv2.imshow("OpenCV warp", warped_image_1_2_cv)
cv2.imshow("Korni warp", warped_image_torch.squeeze().permute(1, 2, 0).cpu().numpy())

cv2.waitKey(0)
cv2.destroyAllWindows()

通过上面的代码，我得到了以下输出：

​

​

使用normalized_coordinates=False，我得到以下输出：

​

​

显然，同形变换的应用是不同的。我很想知道不同之处。

Answer 1

您需要做两个更改：

1. 使用相同的填充模式.

在您的示例中，cv2使用cv2.BORDER_REFLECT101，但是kornia zeros，因此在调用kornia时将zeros更改为padding_mode='reflection'。

需要指定normalized_homography=False.的

所以修改后的版本：

from kornia.geometry.transform.imgwarp import homography_warp
warped_image_torch = homography_warp(image_reshaped, transform_h1_h2, dsize=(height, width), padding_mode="reflection", normalized_homography=False)

或者简单地说：

from kornia.geometry.transform.imgwarp import warp_perspective
warped_image_torch = warp_perspective(image_reshaped, transform_h1_h2, dsize=(height, width), padding_mode="reflection")

结果(cv2/kornia)：

​

​

HomographyWarper内部调用homography_warp函数https://github.com/kornia/kornia/blob/f696d2fb7313474bbaf5e73d8b5a56077248b508/kornia/geometry/transform/homography_warper.py#L96，但HomographyWarper不提供normalized_homography参数，homography_warp提供。

完整的例子：

import cv2
import numpy as np
import torch
from kornia.geometry.transform.imgwarp import warp_perspective, homography_warp


image_cv = cv2.imread("./000000000009.jpg")
image_cv = image_cv[0:256, 0:256]
image = torch.tensor(image_cv).permute(2, 0, 1)
image = image.to("cuda:0")
image_reshaped = image.type(torch.float32).view(1, *image.shape)

height, width, _ = image_cv.shape

homography_0_1 = torch.tensor(
    [
        [7.8783e-01, 3.6705e-02, 2.5139e02],
        [1.6186e-02, 1.0893e00, -2.7614e01],
        [-4.3304e-04, 7.6681e-04, 1.0000e00],
    ],
    device="cuda:0",
    dtype=torch.float64,
)
homography_0_2 = torch.tensor(
    [
        [7.8938e-01, 3.5727e-02, 1.5221e02],
        [1.8347e-02, 1.0921e00, -2.8547e01],
        [-4.3172e-04, 7.7596e-04, 1.0000e00],
    ],
    device="cuda:0",
    dtype=torch.float64,
)
transform_h1_h2 = (
    torch.linalg.inv(homography_0_1)
    .matmul(homography_0_2)
    .type(torch.float32)
    .view(1, 3, 3)
)

# warped_image_torch = homography_warp(image_reshaped, transform_h1_h2, dsize=(height, width), padding_mode="reflection", normalized_homography=False)
warped_image_torch = warp_perspective(image_reshaped, transform_h1_h2, dsize=(height, width), padding_mode="reflection")

warped_image_1_2_cv = cv2.warpPerspective(
    image_cv,
    transform_h1_h2.cpu().numpy().squeeze(),
    dsize=(width, height),
    borderMode=cv2.BORDER_REFLECT101,
)

warped_kornia = warped_image_torch.cpu().numpy().squeeze().transpose(1, 2, 0).astype(np.uint8)
cv2.imwrite("kornia_warp.png", np.hstack((warped_image_1_2_cv, warped_kornia)))