Python 图像膨胀导致亮度下降

我正在尝试使用以下算法实现图像扩展：

1. Zero pad: Put a zero pixel between two pixels
2. Convolve with a column vector of a Gaussian, and multiply by 2
3. Convolve with a row vector of a Gaussian and multiply by 2
4. Return blurred image.

以下是我使用的代码（我使用3表示guassian尺寸）：

以下分别是原始图像和展开图像：

原件：

扩大：

这是gaussian_内核的实现，但我已经验证过，对于内核_size=3，它给出[0.25,0.75,0.25]：

def gaussian_kernel(kernel_size):
    ''' Takes a kernel size that is odd and returns a 2D gaussian
    kernel of this size. Results are undefined for even sizes.
    Arguments:
        kernel_size - The size of the kernel, an odd integer.
    Returns:
        gaussian - A normalized gaussian kernel of given size.
    '''
    if kernel_size == 1:
        return np.array([0,1,0],dtype='float32')
    # Create a gaussian kernel
    gaussian = np.array([1,1],dtype='float32')
    # Convolve it with itself kernel_size times
    convolved = gaussian

    num_of_convolutions = kernel_size-2
    for i in range(0,num_of_convolutions):
        convolved = np.convolve(convolved,gaussian)

    # Normalize it
    sum = convolved.sum()
    nor_gaussian = np.divide(convolved,sum,dtype='float32')


    return np.array([nor_gaussian,]).astype(np.float32)

---

如果在没有“mode”参数的情况下使用ndimage.filters.convalve，则默认情况下会使用“reflect”，这似乎意味着它会反映接近图片末尾的值，这似乎会导致问题。使用“mode=constant”解决了这个问题。

您在哪一行使用“mode=constant”？我看不出有什么问题。将mode=“constant”添加到卷积中，问题就解决了。

def gaussian_kernel(kernel_size):
    ''' Takes a kernel size that is odd and returns a 2D gaussian
    kernel of this size. Results are undefined for even sizes.
    Arguments:
        kernel_size - The size of the kernel, an odd integer.
    Returns:
        gaussian - A normalized gaussian kernel of given size.
    '''
    if kernel_size == 1:
        return np.array([0,1,0],dtype='float32')
    # Create a gaussian kernel
    gaussian = np.array([1,1],dtype='float32')
    # Convolve it with itself kernel_size times
    convolved = gaussian

    num_of_convolutions = kernel_size-2
    for i in range(0,num_of_convolutions):
        convolved = np.convolve(convolved,gaussian)

    # Normalize it
    sum = convolved.sum()
    nor_gaussian = np.divide(convolved,sum,dtype='float32')


    return np.array([nor_gaussian,]).astype(np.float32)