MODERATOR NOTE: a submission to computations art contest, see more: Computational Art Contest 2022 - Staff Picks - WOLFRAM COMMUNITY
8 Likes
Amazing Anton! thank you for sharing. I have been fascinated by this animation since I watched the movie.
1 Like
Congratulations, Anton, this does look like an ink blot. However, when I see the Rorschach mask, I also immediately think of Aleksandr Ivanovich Luzhin from Nabokov’s book “The Defense”.
1 Like
– you have earned Featured Contributor Badge 
Your exceptional post has been selected for our editorial column Staff Picks http://wolfr.am/StaffPicks and Your Profile is now distinguished by a Featured Contributor Badge and is displayed on the Featured Contributor Board. Thank you!
Thank your, Brad!
I think I have some idea why you would associate that Rorschach animation in “mental” chess-players. (I see gryphons and lions, for example…) So, here is another animation with chess figures:
1 Like
Thank you, Ahmed!
And yes, I also have been thinking about that “Rorschach animation effect” since I watched the movie…
Basically, LSA approximations are uniquely fit for doing this kind of effect.
Another approach is to use neural networks in a manner of DeepDream. That is much more computationally expensive, though. (Hence, experimentation would take longer times.)
1 Like
The reasons this “worked” are:
- WL functionalities
- Comprehensive image processing and image effects functionalities
- “Out of the box” parallel programming functionalities
- Without parallel computations making the experiments would have been too slow for me to come up with something “good” within art competition’s deadlines.
- Fast Singular Value Decomposition
- “Out of the box” neural network functionalities
- Computational elements
- Previous work on random graphics generation (mandalas, scribbles)
- Curation, documentation, and availability at Wolfram Function Repository (WFR)
- Having sound design of computation module is important if solutions have to be delivered reliably and quickly.
- Curation, documentation, and availability at Wolfram Function Repository (WFR)
- Previous work on dimension reduction techniques
- Latent Semantic Analysis (LSA) representation is uniquely fit for these kind of effects
- The 3D face reconstruction neural network and related documentation
- Available through Wolfram’s repositories / sites
- Previous work on random graphics generation (mandalas, scribbles)
Here is the corresponding presentation (at YouTube),
“Making of Rorschach mask 2D and 3D animations”:
2 Likes
Halloween version (looks good in “dark mode”):
2 Likes