From e2cb2ec15ec7349910fa544d0c86a2b30b0110c7 Mon Sep 17 00:00:00 2001
From: Cameron
Date: Tue, 25 Oct 2016 16:31:22 -0600
Subject: Update README.md
---
README.md | 29 ++++++++++++++++++++++-------
1 file changed, 22 insertions(+), 7 deletions(-)
diff --git a/README.md b/README.md
index 3000b22..e966c6e 100644
--- a/README.md
+++ b/README.md
@@ -57,9 +57,6 @@ Here we render with an increasing style weight applied to [Red Canna](http://www
### Multiple Style Images
More than one style image can be used to blend multiple artistic styles.
-*Top row (left to right)*: [The Starry Night](https://www.wikiart.org/en/vincent-van-gogh/the-starry-night-1889) + [The Scream](https://www.wikiart.org/en/edvard-munch/the-scream-1893), [The Scream](https://www.wikiart.org/en/edvard-munch/the-scream-1893) + [Composition VII](https://www.wikiart.org/en/wassily-kandinsky/composition-vii-1913), [Seated Nude](http://www.pablopicasso.org/seated-nude.jsp) + [Composition VII](https://www.wikiart.org/en/wassily-kandinsky/composition-vii-1913)
-*Bottom row (left to right)*: [Seated Nude](http://www.pablopicasso.org/seated-nude.jsp) + [The Starry Night](https://www.wikiart.org/en/vincent-van-gogh/the-starry-night-1889), [Oversoul](http://alexgrey.com/art/paintings/soul/oversoul/) + [Freshness of Cold](https://afremov.com/FRESHNESS-OF-COLD-PALETTE-KNIFE-Oil-Painting-On-Canvas-By-Leonid-Afremov-Size-30-x40.html), [David Bowie](http://www.francoise-nielly.com/index.php/galerie/index/56) + [Skull](https://www.wikiart.org/en/jean-michel-basquiat/head)
-
@@ -69,12 +66,12 @@ More than one style image can be used to blend multiple artistic styles.
+*Top row (left to right)*: [The Starry Night](https://www.wikiart.org/en/vincent-van-gogh/the-starry-night-1889) + [The Scream](https://www.wikiart.org/en/edvard-munch/the-scream-1893), [The Scream](https://www.wikiart.org/en/edvard-munch/the-scream-1893) + [Composition VII](https://www.wikiart.org/en/wassily-kandinsky/composition-vii-1913), [Seated Nude](http://www.pablopicasso.org/seated-nude.jsp) + [Composition VII](https://www.wikiart.org/en/wassily-kandinsky/composition-vii-1913)
+*Bottom row (left to right)*: [Seated Nude](http://www.pablopicasso.org/seated-nude.jsp) + [The Starry Night](https://www.wikiart.org/en/vincent-van-gogh/the-starry-night-1889), [Oversoul](http://alexgrey.com/art/paintings/soul/oversoul/) + [Freshness of Cold](https://afremov.com/FRESHNESS-OF-COLD-PALETTE-KNIFE-Oil-Painting-On-Canvas-By-Leonid-Afremov-Size-30-x40.html), [David Bowie](http://www.francoise-nielly.com/index.php/galerie/index/56) + [Skull](https://www.wikiart.org/en/jean-michel-basquiat/head)
### Style Interpolation
When using multiple style images, the degree of blending between the images can be controlled.
-*Top row (left to right)*: content image, .2 [The Starry Night](https://www.wikiart.org/en/vincent-van-gogh/the-starry-night-1889) + .8 [The Scream](https://www.wikiart.org/en/edvard-munch/the-scream-1893), .8 [The Starry Night](https://www.wikiart.org/en/vincent-van-gogh/the-starry-night-1889) + .2 [The Scream](https://www.wikiart.org/en/edvard-munch/the-scream-1893)
-*Bottom row (left to right)*: .2 [Oversoul](http://alexgrey.com/art/paintings/soul/oversoul/) + .8 [Freshness of Cold](https://afremov.com/FRESHNESS-OF-COLD-PALETTE-KNIFE-Oil-Painting-On-Canvas-By-Leonid-Afremov-Size-30-x40.html), .5 [Oversoul](http://alexgrey.com/art/paintings/soul/oversoul/) + .5 [Freshness of Cold](https://afremov.com/FRESHNESS-OF-COLD-PALETTE-KNIFE-Oil-Painting-On-Canvas-By-Leonid-Afremov-Size-30-x40.html), .8 [Oversoul](http://alexgrey.com/art/paintings/soul/oversoul/) + .2 [Freshness of Cold](https://afremov.com/FRESHNESS-OF-COLD-PALETTE-KNIFE-Oil-Painting-On-Canvas-By-Leonid-Afremov-Size-30-x40.html)
@@ -84,16 +81,18 @@ When using multiple style images, the degree of blending between the images can
+*Top row (left to right)*: content image, .2 [The Starry Night](https://www.wikiart.org/en/vincent-van-gogh/the-starry-night-1889) + .8 [The Scream](https://www.wikiart.org/en/edvard-munch/the-scream-1893), .8 [The Starry Night](https://www.wikiart.org/en/vincent-van-gogh/the-starry-night-1889) + .2 [The Scream](https://www.wikiart.org/en/edvard-munch/the-scream-1893)
+*Bottom row (left to right)*: .2 [Oversoul](http://alexgrey.com/art/paintings/soul/oversoul/) + .8 [Freshness of Cold](https://afremov.com/FRESHNESS-OF-COLD-PALETTE-KNIFE-Oil-Painting-On-Canvas-By-Leonid-Afremov-Size-30-x40.html), .5 [Oversoul](http://alexgrey.com/art/paintings/soul/oversoul/) + .5 [Freshness of Cold](https://afremov.com/FRESHNESS-OF-COLD-PALETTE-KNIFE-Oil-Painting-On-Canvas-By-Leonid-Afremov-Size-30-x40.html), .8 [Oversoul](http://alexgrey.com/art/paintings/soul/oversoul/) + .2 [Freshness of Cold](https://afremov.com/FRESHNESS-OF-COLD-PALETTE-KNIFE-Oil-Painting-On-Canvas-By-Leonid-Afremov-Size-30-x40.html)
### Transfer style but not color
The color scheme of the original image can be preserved by including the flag `--original_colors`.
-*Left to right*: content image, stylized image, stylized image with the original colors of the content image
+*Left to right*: content image, stylized image, stylized image with the original colors of the content image
### Textures
The algorithm is not constrained to artistic painting styles. It can also be applied to photographic textures to create [pareidolic](https://en.wikipedia.org/wiki/Pareidolia) images.
@@ -129,7 +128,6 @@ Style can be transferred to semantic segmentations in the content image.
Multiple styles can be transferred to the foreground and background of the content image.
-*Left to right*: content image, foreground style, background style, foreground mask, background mask, stylized image
@@ -145,6 +143,7 @@ Multiple styles can be transferred to the foreground and background of the conte
+*Left to right*: content image, foreground style, background style, foreground mask, background mask, stylized image
### Video
Animations can be rendered by applying the algorithm to each source frame. For the best results, the network is initialized with the previously stylized frame warped to the current frame according to the optical flow between the pair of frames. Loss functions for temporal consistency are used to penalize pixels excluding disoccluded regions and motion boundaries.
@@ -155,6 +154,22 @@ Animations can be rendered by applying the algorithm to each source frame. For
+### Gradient Descent Initialization
+The gradient descent is controlled using `--init_img_type` for single images and `--init_frame_type` and `--init_first_frame_type` for video frames. For a single image, the gradient descent can be initialized with white noise `random`, the content image `content`, or the style image `style`. For video frames, the gradient descent can also be initialized with the previous stylized frame `prev` or the previous stylized frame warped to the current frame `prev_warp`. White noise allows an arbitrary number of distinct images to be generated. Whereas, initializing with a fixed image converges to the same output.
+
+Here we reproduce Figure 6 from the first paper:
+
+
+
+
+
+
+
+
+
+*Top row (Left to right)*: Initialized with the content image, the style image, white noise with `--seed 1`
+*Bottom row (Left to right)*: white noise with `--seed 2`, white noise with `--seed 3`, white noise with `--seed 4`
+
## Setup
#### Dependencies:
* [tensorflow](https://github.com/tensorflow/tensorflow)
--
cgit v1.2.3-70-g09d2
From 47bc434f16c294f0ff2a89dedefa19e6f730bde2 Mon Sep 17 00:00:00 2001
From: Cameron
Date: Tue, 25 Oct 2016 16:32:59 -0600
Subject: Update README.md
---
README.md | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/README.md b/README.md
index e966c6e..11e91a2 100644
--- a/README.md
+++ b/README.md
@@ -155,7 +155,7 @@ Animations can be rendered by applying the algorithm to each source frame. For
### Gradient Descent Initialization
-The gradient descent is controlled using `--init_img_type` for single images and `--init_frame_type` and `--init_first_frame_type` for video frames. For a single image, the gradient descent can be initialized with white noise `random`, the content image `content`, or the style image `style`. For video frames, the gradient descent can also be initialized with the previous stylized frame `prev` or the previous stylized frame warped to the current frame `prev_warp`. White noise allows an arbitrary number of distinct images to be generated. Whereas, initializing with a fixed image converges to the same output.
+The gradient descent is controlled using `--init_img_type` for single images and `--init_frame_type` or `--init_first_frame_type` for video frames. For a single image, the gradient descent can be initialized with white noise `random`, the content image `content`, or the style image `style`. For video frames, the gradient descent can also be initialized with the previous stylized frame `prev` or the previous stylized frame warped to the current frame `prev_warp`. White noise allows an arbitrary number of distinct images to be generated. Whereas, initializing with a fixed image converges to the same output.
Here we reproduce Figure 6 from the first paper:
@@ -167,8 +167,8 @@ Here we reproduce Figure 6 from the first paper:
-*Top row (Left to right)*: Initialized with the content image, the style image, white noise with `--seed 1`
-*Bottom row (Left to right)*: white noise with `--seed 2`, white noise with `--seed 3`, white noise with `--seed 4`
+*Top row (Left to right)*: Initialized with the content image, the style image, white noise & `--seed 1`
+*Bottom row (Left to right)*: Initialized with white noise & `--seed 2`, white noise & `--seed 3`, white noise & `--seed 4`
## Setup
#### Dependencies:
--
cgit v1.2.3-70-g09d2
From 641064170f8097effc8f77fa8e840201278ae9af Mon Sep 17 00:00:00 2001
From: Cameron
Date: Tue, 25 Oct 2016 16:33:46 -0600
Subject: Update README.md
---
README.md | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/README.md b/README.md
index 11e91a2..c2e051d 100644
--- a/README.md
+++ b/README.md
@@ -167,8 +167,8 @@ Here we reproduce Figure 6 from the first paper:
-*Top row (Left to right)*: Initialized with the content image, the style image, white noise & `--seed 1`
-*Bottom row (Left to right)*: Initialized with white noise & `--seed 2`, white noise & `--seed 3`, white noise & `--seed 4`
+*Top row (Left to right)*: Initialized with the content image, the style image, white noise `--seed 1`
+*Bottom row (Left to right)*: Initialized with white noise `--seed 2`, white noise `--seed 3`, white noise `--seed 4`
## Setup
#### Dependencies:
--
cgit v1.2.3-70-g09d2
From 88fa820f32e7d6ce0351c2d85ea9144294993ea7 Mon Sep 17 00:00:00 2001
From: Cameron
Date: Tue, 25 Oct 2016 16:34:55 -0600
Subject: Update README.md
---
README.md | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/README.md b/README.md
index c2e051d..3ebfb19 100644
--- a/README.md
+++ b/README.md
@@ -155,7 +155,7 @@ Animations can be rendered by applying the algorithm to each source frame. For
### Gradient Descent Initialization
-The gradient descent is controlled using `--init_img_type` for single images and `--init_frame_type` or `--init_first_frame_type` for video frames. For a single image, the gradient descent can be initialized with white noise `random`, the content image `content`, or the style image `style`. For video frames, the gradient descent can also be initialized with the previous stylized frame `prev` or the previous stylized frame warped to the current frame `prev_warp`. White noise allows an arbitrary number of distinct images to be generated. Whereas, initializing with a fixed image converges to the same output.
+The initialization of the gradient descent is controlled using `--init_img_type` for single images and `--init_frame_type` or `--init_first_frame_type` for video frames. For single images, the gradient descent can be initialized with white noise `random`, the content image `content`, or the style image `style`. For video frames, the gradient descent can also be initialized with the previous stylized frame `prev` or the previous stylized frame warped to the current frame `prev_warp`. White noise allows an arbitrary number of distinct images to be generated. Whereas, initializing with a fixed image converges to the same output.
Here we reproduce Figure 6 from the first paper:
--
cgit v1.2.3-70-g09d2
From b4fd59d807eebccb394aeaf70c4eb02a03e0d010 Mon Sep 17 00:00:00 2001
From: Cameron
Date: Tue, 25 Oct 2016 16:38:10 -0600
Subject: Update README.md
---
README.md | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/README.md b/README.md
index 3ebfb19..1c79909 100644
--- a/README.md
+++ b/README.md
@@ -155,7 +155,7 @@ Animations can be rendered by applying the algorithm to each source frame. For
### Gradient Descent Initialization
-The initialization of the gradient descent is controlled using `--init_img_type` for single images and `--init_frame_type` or `--init_first_frame_type` for video frames. For single images, the gradient descent can be initialized with white noise `random`, the content image `content`, or the style image `style`. For video frames, the gradient descent can also be initialized with the previous stylized frame `prev` or the previous stylized frame warped to the current frame `prev_warp`. White noise allows an arbitrary number of distinct images to be generated. Whereas, initializing with a fixed image converges to the same output.
+The initialization of the gradient descent is controlled using `--init_img_type` for single images and `--init_frame_type` or `--init_first_frame_type` for video frames. For single images, the gradient descent can be initialized with white noise, the content image, or the style image. For video frames, the gradient descent can also be initialized with the previous stylized frame or the previous stylized frame warped to the current frame. White noise allows an arbitrary number of distinct images to be generated. Whereas, initializing with a fixed image always converges to the same output.
Here we reproduce Figure 6 from the first paper:
@@ -167,8 +167,8 @@ Here we reproduce Figure 6 from the first paper:
-*Top row (Left to right)*: Initialized with the content image, the style image, white noise `--seed 1`
-*Bottom row (Left to right)*: Initialized with white noise `--seed 2`, white noise `--seed 3`, white noise `--seed 4`
+*Top row (Left to right)*: Initialized with the content image, the style image, white noise (seed 1)
+*Bottom row (Left to right)*: Initialized with white noise (seed 2), white noise (seed 3), white noise (seed 4)
## Setup
#### Dependencies:
--
cgit v1.2.3-70-g09d2
From dbb23404ccf87cbb90d1fc4b6dfe9449ce5511e0 Mon Sep 17 00:00:00 2001
From: Cameron
Date: Tue, 25 Oct 2016 16:42:15 -0600
Subject: Update README.md
---
README.md | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/README.md b/README.md
index 1c79909..d7aa978 100644
--- a/README.md
+++ b/README.md
@@ -159,13 +159,13 @@ The initialization of the gradient descent is controlled using `--init_img_type`
Here we reproduce Figure 6 from the first paper:
-
-
-
+
+
+
-
-
-
+
+
+
*Top row (Left to right)*: Initialized with the content image, the style image, white noise (seed 1)
*Bottom row (Left to right)*: Initialized with white noise (seed 2), white noise (seed 3), white noise (seed 4)
--
cgit v1.2.3-70-g09d2
From 79f30b0c8e35d2eb8dcb12a5677764e8c195b1d8 Mon Sep 17 00:00:00 2001
From: Cameron
Date: Tue, 25 Oct 2016 16:43:11 -0600
Subject: Update README.md
---
README.md | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/README.md b/README.md
index d7aa978..612fddf 100644
--- a/README.md
+++ b/README.md
@@ -162,7 +162,8 @@ Here we reproduce Figure 6 from the first paper:
-
+
+
--
cgit v1.2.3-70-g09d2
From f2b9a0798afdc5d2d190272a388272bf133fe9cd Mon Sep 17 00:00:00 2001
From: Cameron
Date: Tue, 25 Oct 2016 16:46:19 -0600
Subject: Update README.md
---
README.md | 9 ++-------
1 file changed, 2 insertions(+), 7 deletions(-)
diff --git a/README.md b/README.md
index 612fddf..03f180b 100644
--- a/README.md
+++ b/README.md
@@ -161,15 +161,10 @@ Here we reproduce Figure 6 from the first paper:
-
-
-
+
-
-
-*Top row (Left to right)*: Initialized with the content image, the style image, white noise (seed 1)
-*Bottom row (Left to right)*: Initialized with white noise (seed 2), white noise (seed 3), white noise (seed 4)
+*Left to right*: Initialized with the content image, the style image, white noise (seed 1), white noise (seed 2)
## Setup
#### Dependencies:
--
cgit v1.2.3-70-g09d2
From bbddd8aa47b8449da053a4102a1477f85ed7b728 Mon Sep 17 00:00:00 2001
From: Cameron
Date: Tue, 25 Oct 2016 16:48:43 -0600
Subject: Update README.md
---
README.md | 14 +++++++++-----
1 file changed, 9 insertions(+), 5 deletions(-)
diff --git a/README.md b/README.md
index 03f180b..e7a5c07 100644
--- a/README.md
+++ b/README.md
@@ -159,12 +159,16 @@ The initialization of the gradient descent is controlled using `--init_img_type`
Here we reproduce Figure 6 from the first paper:
-
-
-
-
+
+
+
+
+
+
+
-*Left to right*: Initialized with the content image, the style image, white noise (seed 1), white noise (seed 2)
+*Top row (left to right)*: Initialized with the content image, the style image, white noise (seed 1)
+*Bottom row (left to right)*: Initialized with white noise (seed 2), white noise (seed 3), white noise (seed 4)
## Setup
#### Dependencies:
--
cgit v1.2.3-70-g09d2
From b00ee8adabc67c9a2d5162c28a8ca0c7dfe7cef8 Mon Sep 17 00:00:00 2001
From: Cameron
Date: Tue, 25 Oct 2016 16:58:44 -0600
Subject: Update README.md
---
README.md | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/README.md b/README.md
index e7a5c07..360ae2d 100644
--- a/README.md
+++ b/README.md
@@ -167,8 +167,8 @@ Here we reproduce Figure 6 from the first paper:
-*Top row (left to right)*: Initialized with the content image, the style image, white noise (seed 1)
-*Bottom row (left to right)*: Initialized with white noise (seed 2), white noise (seed 3), white noise (seed 4)
+*Top row (left to right)*: Initialized with the content image, the style image, white noise (RNG seed 1)
+*Bottom row (left to right)*: Initialized with white noise (RNG seed 2), white noise (RNG seed 3), white noise (RNG seed 4)
## Setup
#### Dependencies:
--
cgit v1.2.3-70-g09d2