Closed leedewdew closed 1 year ago
You can use segmentation prediction networks and blend the results with the originla frame,
Good idea. Bu it works when the mask of generated image is larger than that of original image, while in the other case(the former is smaller), it maybe won't.
I cannot understand you question. The output image (and the mask) should be always no larger than the whole image. Our method does not create new content, but only relies on the input image.
Sorry, I means when the portrait mask of stylized image is smaller than the human mask of the original image, directly use stylized segmentation mask doesn't match the size of the mask of the original image.
Can you give some image example of what the portrait mask/human mask/stylized segmentation mask/mask of the original image look like? There are many masks in your description.
You can use segmentation prediction networks and blend the results with the originla frame,
Human mask of original image and stylized image don't match in size.
Maybe you can use a dilated stylized mask, and smooth the mask boundary to alliviate the mismatches of the two masks
Ok, Thank you.
Thanks for your great job. I have a question about how to keep background area while stylizing portrait area? Looking for your reply.