Final Project I - Lightfield Camera
Final Project II - A Neural Algorithm for Style Transfer
depth
, using which we control the amount of the shift, and thus the depth we focus on. In the
resulting image, this shows up as a refocused area corresponding to that depth.
Depth = -0.1 |
Depth = 0.0 |
Depth = 0.1 |
Depth = 0.2 |
Depth = 0.3 |
Depth = 0.4 |
Depth = 0.5 |
r = 0
means we sample only the center image. Here are the results
(setting depth=0.20
to focus on the center region):
r = 0 |
r = 10 |
r = 20 |
r = 30 |
r = 40 |
r = 50 |
refocus_im
function implemented in Part 1, I also created a function that allows us
to refocus on any point of the image.
The function takes in the (u, v) coordinates of the point, which can be easily read from skio
's
image output. It then calculates the optimal depth for refocusing.
For example, we have the following blurry image:
VGG19_Weights.IMAGENET1K_V1
.
Berkeley, CA |
Golden Gate Bridge 1 |
Golden Gate Bridge 2 |
The Starry Night, Vincent van Gogh |
Impression, Sunrise, Claude Monet |
Haystacks, Claude Monet |
The Scream, Edvard Munch |
Figure, Pablo Picasso |
Journey to the East, Bukang Y. Kim |
Berkeley + Starry |
Berkeley + Scream |
Berkeley + Sunrise |
Berkeley + Cubism |
Bridge + Scream |
Bridge 2 + Haystacks |
Berkeley + Ink Wash |
Approach 1style_layers = [0, 5, 10, 19, 28]content_layers = [25] |
Approach 2style_layers = [2, 7, 12, 21, 30]content_layers = [22, 25] |
Approach 1style_layers = [0, 5, 10, 19, 28]content_layers = [25] |
Approach 2style_layers = [2, 7, 12, 21, 30]content_layers = [22, 25] |