CITE THIS NOTEBOOK: Details in Rorschach mask animations making by Anton Antonov. Wolfram Community NOV 1 2022.
MathematicaForPrediction at WordPress​
​MathematicaForPrediction at GitHub​
​SimplifiedMachineLearningWorkflows-book at GitHub
Presentation at YouTube

Presentation plan

The presentation follows the following flowchart:
Out[]=

2D animations

Here is a “clouds on cloth” 2D animation:
Out[]=
Here is a “oil painting” effect 2D animation:
Out[]=

3D animation

The following 3D animation is derived
◼
  • Using imposition of 2D animation images over 3D object (human head) derived using a 3D "volumetric approximation" neural network
    • ◼
  • Differently stretched versions of the 2D animation images are used
    • ◼
  • The frames of each 3D movie were “transposed” and image assembly was applied on the corresponding rows
    • In[]:=
    Video["https://i.imgur.com/IXMFWnW.mp4"]
    Out[]=
    (Also, see https://i.imgur.com/IXMFWnW.gif .)

    "Watchmen: Rorschach's Mask" (YouTube)

    Discussion at YouTube (The Hollywood Reporter):

    RandomRorschach

    Examples of the Wolfram Function Repository (WFR) function:
    In[]:=
    ResourceFunction["RandomRorschach"][]
    Out[]=
    In[]:=
    ResourceFunction["RandomRorschach"][]
    Out[]=
    In[]:=
    Multicolumn@Table[ResourceFunction["RandomRorschach"]["NumberOfStrokes"->{12,16,9},"OrderedStrokePoints"->RandomChoice[{False,True}],ColorFunction->(Black&),"ImageEffects"->Automatic],24]
    Out[]=
    ​

    Rorschach collection

    In this section we make the main computational workflow for 2D animation.

    Get data

    Here we generate the training images data. (We experiment with small image sizes, and we get good results we large image sizes.)
    Remark: The function PrepareImageData is from the package [AAp1].

    Apply LSA

    Here we apply LSA dimension reduction. (See [AA1-AA5].)
    Get the image basis and show a sample:

    Random Rorschach motion

    Pick a target image and pre-process it:
    Find its representation with chosen feature extractor (LSAMon object here):

    Guided Rorschach motion

    3D reconstruction

    Here we go through the 3D head-from-face reconstruction described in ”Facial 3D Reconstruction ".

    Load packages

    References

    Articles

    [AA1] Anton Antonov, "A monad for Latent Semantic Analysis workflows", (2019), Wolfram Community.
    [AA2] Anton Antonov, "LSA methods comparison over random mandalas deconstruction -- WL", (2022), Wolfram Community.
    [AA3] Anton Antonov, "Bethlehem stars: classifying randomly generated mandalas", (2020), Wolfram Community.
    [AA4] Anton Antonov, "[LiVE] Latent Semantic Analysis Workflows (WL Live-Stream Series)", (2019), Wolfram Community.
    [AA5] Anton Antonov, "Re-exploring the structure of Chinese character images​", (2022), Wolfram Community.

    Functions

    [AAf1] Anton Antonov, "RandomRorschach", (2022), Wolfram Function Repository.
    [AAf2] Anton Antonov, "RandomScribble", (2021), Wolfram Function Repository.
    [AAf3] Anton Antonov, "RandomMandala", (2019), Wolfram Function Repository.

    Packages

    [AAp1] Anton Antonov, LSAMon for Image Collections Mathematica package, (2022), MathematicaForPrediction at GitHub.

    Videos

    [AAv1] Anton Antonov, "Making of Rorschach mask 2D and 3D animations", (2022), Anton Antonov's YouTube channel.