Skip to yearly menu bar Skip to main content



in
Session: Creative AI Session 3

Q's Views #1-#3 (+1)

Hall D1 (level 1) Table 4
[ ]
Thu 14 Dec 8:45 a.m. PST — 12:15 p.m. PST

Abstract:

Q's Views #1-#3 are part of an ongoing series of digital still images that aim to provide a visual experience of the unbridgeable gap between believers and non-believers of conspiracy theories in today's surreal socio-political situations in the post-truth world, through hybrid image portraits synthesized from AI-generated "fake" images of Hillary Clinton.

Hybrid image is a technique for creating an image that is perceived as one image from afar, but as another image up close, using an optical illusion based on the way the human visual system performs multi-scale processing of images.

For each work, we use generative AI to create a normal portrait of Hillary Clinton and then transform it into a grotesque variant based on conspiracy theories. These images are then synthesized into a hybrid image to embed an optical illusion in which a normal portrait of her suddenly transforms into a grotesque variant when the viewer approaches.

Therefore, as viewers come closer to the threshold of visual perception of the hybrid image, the artwork triggers a sudden realization that conspiracy theorists perceive Hillary Clinton as an entirely different person, thus accentuating the insurmountable divergence in perceived realities between believers and non-believers of conspiracy theories. It is important to acknowledge that even the "normal" portraits themselves are AI-generated fabrications, rendering them as fake images devoid of authenticity. In this work, nothing is genuine, and everything is deliberately fabricated.

As artworks of visual sarcasm, Q's Views #1-#3 refer to our post-truth era, where facts and reality must be all questioned, as generative AIs are used to produce high-fidelity images for fake news and propaganda today, significantly enhancing alienation and division in perceived realities in the same world that we share.

Thus, the work refers to uncanny diversity in perceived realities in our post-truth era. People see what they want to see; now they can even create what they want to see by generative AIs.

NOTE: Since some people value politics over artistry in evaluating artwork, a 'sneak preview' of a prototype from another ongoing hybrid-image portrait series is also showcased at NeurIPS 2023, to satisfy their political preferences

Chat is not available.