Image feathering

Weight each image proportional to its distance from the edge
(distance map [Danielsson, CVGIP 1980]

1. Generate weight map for each image

2. Sum up all of the weights and divide by sum:
weights sum up to 1: w_i’ = w_i / ( ∑_i w_i)

Slide 3

Laplacian image blend

Compute Laplacian pyramid

Compute Gaussian pyramid on weight image (can put this in A channel)

Blend Laplacians using Gaussian blurred weights

Reconstruct the final image

Q: How do we compute the original weights?

A: For horizontal panorama, use mid-lines

Q: How about for a general “3D” panorama?

Weight selection (3D panorama)

Idea: use original feather weights to select
strongest contributing image

Can be implemented using L-∞ norm: (p = 10)

w_i’ = [w_i^p / ( ∑_i w_i^p)]^1/^p


	Weight each image proportional to its distance from the edge (distance map [Danielsson, CVGIP 1980]


	1. Generate weight map for each image
	2. Sum up all of the weights and divide by sum: weights sum up to 1: w_i’ = w_i / ( ∑_i w_i)


	Compute Laplacian pyramid
	Compute Gaussian pyramid on weight image (can put this in A channel)
	Blend Laplacians using Gaussian blurred weights
	Reconstruct the final image
	Q: How do we compute the original weights?
	A: For horizontal panorama, use mid-lines
	Q: How about for a general “3D” panorama?


	Idea: use original feather weights to select strongest contributing image




	Can be implemented using L-∞ norm: (p = 10)
	w_i’ = [w_i^p / ( ∑_i w_i^p)]^1/^p