I am passionate about thinking of how creative expression mediums can be expanded, and within this increasing technologically occupied world we live in, how can creative expression, something that is so innate to us, be maintained. Not only maintained, but also mediated through advancements in technology. As much as art and creativity are about an internal drive and expression desire, it is also about tools used to create it and the media through which it gets delivered. Art has always existed in a continuously evolving and complex relationship with the technological capabilities of a time. While some artists seek benefits from its advancements, others abstain from it to maintain traditional practices, but its fusion in the representation of an art generation is inevitable.
A lot of the work i have done, ‘protopiper, flying pantograph, traditional CAD, fabcode, fractal-kits, bungee-music, poetry wanderings, essence of reminiscence, tact-art, have all been these attempts at seeing how we can create new ways of creative expression.
Looking at the advancements in deep learning, i am curious, how it can become a conversational art medium. How can one interact with a computer capable of visual imagination to create art works?
The system i am collaborating on for this is called Tandem!
The idea is to take a human sketch/ painting as an input and let a neural network ‘imagine’ on it. The human also communicates to this computer collaborator, some aspects of personality (with a relaxed definition of personality) like happy, sad, dark, even painting styles like cubism etc. The output from the neural network that imagines on the input, is then used as an input in a style transfer implementation that is then presented to the human on top of their input. The human can then tweak their input, and continue this conversation.
Here’s a video where we combine the act of painting with a computer collaborator into a single physical space:
Here are some of the other outputs produced using Tandem:
In the first image, a person drew something with an intention of it being trees, but the computer imagined them something on the lines of dogs!
Here a person drew the Barad-dûr, with a dark and angry personality selected. The person then later added the ash mountains.
Some more outputs:
Here’s some new experiments with drawing cultural objects:
I have also been very interested in how style transfer techniques can be used in terms of creating cultural hybrids.
Here are some initial experiments with adding patterns from different cultures to the Dakishi T-shirt from Africa.
Here’s with an aboriginal pattern:
Here’s one with a mask!