Simple one-line Domain Transform filter call

dst = cv.DTFilter.dtFilter(src, guide)
dst = cv.DTFilter.dtFilter(src, guide, 'OptionName',optionValue, ...)

Input

• src filtering image with unsigned 8-bit or floating-point 32-bit depth and up to 4 channels.
• guide guided image (also called as joint image) with unsigned 8-bit or floating-point 32-bit depth and up to 4 channels.

Output

• dst destination image.

Options

• SigmaSpatial sigma_H parameter in the original article, it's similar to the sigma in the coordinate space into cv.bilateralFilter. default 10.0
• SigmaColor sigma_r parameter in the original article, it's similar to the sigma in the color space into cv.bilateralFilter. default 25.0
• Mode one form three modes which corresponds to three modes for filtering 2D signals in the article. default 'NC':
  • NC Normalized Convolution (NC).
  • IC Interpolated Convolution (IC).
  • RF Recursive Filtering (RF).
• NumIters optional number of iterations used for filtering, 3 is quite enough. default 3

If you have multiple images to filter with the same guided image then use DTFilter interface to avoid extra computations on initialization stage.