BasicNotebook

A very basic notebook that displays a message. No AI code, just a demo of the publishing system used. It first prompts the user to upload an image, then resizes it and draws some text.

ContentReconstructionSurvey

Reconstructs an example image's content via each layer of the VGG19 network. Paints an image using a variety of layers but each having:
  1. A single input image to define content via a single layer
  2. Random noise initialization
  3. Standard content matching operator
  4. A single resolution
It demonstrates the variety of effects that can be obtained using varied layers to constrain content.

TextureSurvey

Reconstructs an example image's texture into free-form content via each layer of the VGG19 network. Paints a texture using a variety of layers but each having:
  1. A single input image to define style
  2. Random noise initialization
  3. Operators to match content and constrain and enhance style
  4. A single resolution
It demonstrates the variety of effects that can be obtained using varied layers.

OperatorSurvey

Paints a texture using a variety of signal operators but each having:
  1. A single input image to define style
  2. Random noise initialization
  3. Standard VGG16 layers to define the style
  4. A single resolution
It demonstrates the variety of effects that can be obtained using varied operators.

TextureGrowth

Paints a texture using a variety of resolution schedules, each with:
  1. A single input image to define style
  2. Random noise initialization
  3. Standard VGG16 layers to define the style
  4. Operators to match content and constrain and enhance style
Demonstrates the effect of iteratively repainting while magnifying an image.

SeedImageSurvey

Reconstructs a style texture using a variety of seed images but each having:
  1. A single input image to define style
  2. Standard VGG16 layers to define the style
  3. Operators to match content and constrain and enhance style
  4. A single resolution
It demonstrates the variety of effects that can be obtained using varied starting canvas seeds.

TiledTexture

Creates a simple tiled texture based on a style using:
  1. Random plasma initialization
  2. Standard VGG16 layers
  3. Operators constraining and enhancing style
  4. Progressive resolution increase
  5. View layer to enforce tiling

TextureTiledRotor

Creates a tiled and rotationally symmetric texture based on a style using:
  1. Random noise initialization
  2. Standard VGG16 layers
  3. Operators constraining and enhancing style
  4. Progressive resolution increase
  5. Kaleidoscopic view layer in addition to tiling layer

TextureStereogram

Creates simple stereogram based on a very tall tiled texture rendered using:
  1. Random plasma initialization
  2. Standard VGG16 layers
  3. Operators constraining and enhancing style
  4. Progressive resolution increase
  5. View layer to enforce tiling
  6. Final rendering process combining the texture with a depth map to produce a stereogram

DeepDream

Implements the DeepDream image processing algorithm:
  1. Start from an input image
  2. Use the final layer of an inception network
  3. Operator to maximize RMS signal
  4. Single resolution

HighResStyleTransfer

Paints an image in the style of another using multiple resolution phases, each with tuned parameters. The result is a high resolution, high quality rendered painting.

StyleTransfer

Paints an image in the style of another using:
  1. Random plasma initialization
  2. Standard VGG16 layers
  3. Operators to match content and constrain and enhance style
  4. Progressive resolution increase

AnimatedStyleTransfer

Paints a series of images, each to match the content of one while in the style of another using:
  1. Random noise initialization
  2. Standard VGG16 layers
  3. Operators to match content and constrain and enhance style
  4. Progressive resolution increase
The parameters for each frame are fixed, but due to the random initialization and loose constraints we can achive a dynamic effect.

AnimatedRotor

Paints a series of images, each to match the content of one while in the style of another using:
  1. Random noise initialization
  2. Standard VGG16 layers
  3. Operators to match content and constrain and enhance style
  4. Progressive resolution increase
  5. Rotational symmerty constraint caused by a kaliedoscopic image layer
The parameters for each frame are fixed, but due to the random initialization and loose constraints we can achive a dynamic effect.

StyleTransferSweep

Paints a series of images, each to match the content of one while using:
  1. A linear combination of two styles
  2. Random noise initialization
  3. Standard VGG16 layers
  4. Operators to match content and constrain and enhance style
  5. Progressive resolution increase
The parameters for each frame are fixed and randomly initialized, but the style used sweeps between two reference images over the animation.

SmoothStyle

Paints an image in the style of another using:
  1. PhotoSmooth-based content initialization
  2. Standard VGG16 layers
  3. Operators to match content and constrain and enhance style
  4. Progressive resolution increase

SegmentStyle

Demonstrates application of style transfer to a masked region identified by user scribble