The application discloses an
image processing method, device and
electronic equipment, and the method comprises the steps of acquiring a wide depth-of-field image, depth information corresponding to the wide depth-of-field image, a foreground cutout and an initial
light spot; inputting the wide depth-of-field image and first focus guide information generated based on the depth information into a first blurring network for
processing to obtain a basic blurred image; inputting the wide depth-of-field image, second focus guide information generated based on the depth information, the foreground cutout and the basic blurred image into a second blurring network for
processing to obtain an optimized blurred image; inputting the optimized blurred image, third focus guide information generated based on the depth information and the initial
light spot into a
light spot mask network for
processing to obtain a stylized light spot
mask; processing the initial light spot according to the stylized light spot
mask to generate a stylized light spot; and performing fusion processing on the optimized blurred image, the stylized light spot and the wide depth-of-field
image based on the depth information to obtain a shallow depth-of-field image.