World’s first AI Artathon enters final round

90 views



Saudi Gazette report

RIYADH — Ten finalists were announced for the AI Artathon during a live stream event on Tuesday to showcase artworks created by artists and AI developers using artificial intelligence tools and techniques.

The announcement of the winners will take place during the Global AI Summit on Oct. 22. The three winning teams will split a prize of SR500,000 ($133,000).

The AI Artathon, the first of its kind initiated by the Kingdom, is one of the Global AI Summit’s initiatives that aim to highlight the creative potential of humans and machines working together to create art.

Over 2,000 candidates from more than 50 countries applied to participate, of which only 300 were selected to form 20 teams. They were selected based on an Artathon round held in Riyadh in January, and they include artists, graphic designers, AI experts, and programmers.

In the first phase, participants competed to create initial AI-based artworks. They were then engaged in a boot camp to be trained by experts to use machine learning algorithms and generative adversarial networks (GAN) to create art.

The AI Artathon is organized by the Saudi Data & AI Authority (SDAIA), as part of the Global AI Summit. The GAIS, which is being held virtually on Oct. 21-22, will bring together key decision-makers from government, academia, business, and technology, to discuss global issues and challenges facing humanity and how AI can play a role for the good of humanity and in shaping the new normal.

In this regard, Dr. Abdullah Bin Sharaf Al-Ghamdi, the President of SDAIA, and the chairman of the organizing committee of the Global AI Summit, said: “SDAIA is proud of these high-quality artworks created by the finalists of the AI Artathon. I am very pleased to see artists and AI developers collaborating to utilize the capabilities of advanced AI to create these innovative artworks, despite the novel coronavirus pandemic. I look forward to announcing the final winners during the Global AI Summit.”

The final ten teams are:

Saudi Picasso

The idea of this artwork was “what if Picasso was Saudi?” The team created a database that consists of Picasso’s and Saudi artworks to enable the machine to create a new piece that highlights the depth, richness and diversity of Saudi art.

Emergent Typographies

Reflecting the beauty of the Kingdom’s nature, the artists used geographic and topographic graphics as well as existing lines and shapes to train AI to combine them to create a new digital artwork in which new patterns and inspirations are made.

Maruem — The Chimera Ant Queen

Inspired by a popular anime, and the character and traits of the ‘Chimera Ant’, this project uses digital graffiti and other artworks and concepts to create a unique new piece that follows the journey of a Chimera Ant from cell to birth.

AI Authentic clay

Personality is usually the result of knowledge accumulation, e.g., culture, religion, and civilization. The creators of this artwork express their deep feelings towards the authenticity of their culture, presenting experience from a new scope by combining and reorganizing several shapes and patterns through AI.

Esoteric & Energetic "Heya"

Words have certain meanings, energies and inspirations; "Heya", in English ‘she’, has many meanings. She is a daughter, sister, mother, hard-working, etc. This artwork is inspired by Heya’s energy, feelings, and strength. The team took selfies of women representing diversity as well as drawings for the word ‘she’. AI technologies were used to analyze and link these photos and drawings to create a new unique digital art piece.

The Beauty of Belonging

As architecture is a fundamental characteristic of any cultural production that enhances the sense of belonging, this artwork aims to shed light on the richness and variety of Saudi culture’s architecture. Different architectural styles and patterns are combined and integrated using AI algorithms to produce an artwork with a new color and style, creating an abstract visual experience.

Museum of GANs

What if we could depict the emotional states and impressions about a character from portraits? And what if we could create new artworks based on different emotional states? This artwork tries to answer these questions after collecting and classifying a large number of well-known portraits according to their emotional states and impressions on which the machine contributed to creating the artwork.

Machine Mythology

As humans, when we read a text, there will always be intertextualities and associations to perceptions, figures, etc., in our minds. In this artwork, the team developed a model that enables the machine to read these associations using AI. A random text generator was used to write stories that are developed to transform the textual into visual.

Ultimate Pattern

Different architectural shapes and styles have developed over time around the Arab world and they are used in buildings, mosques and landmarks, creating a characteristic unique to the Arab art. The team developed a single aesthetic pattern that combines many different patterns to reach the one that has the best comprehensive picture. Patterns are processed via DCGAN, which in turn, classifies, connects, develops, and redraws shapes to enable the machine to create a new art piece.

0What distinguishes AI digital art is its limitless capabilities to recognize and translate human creativity. Taking the novel as a crucial element in literary creativity, this artwork is the result of an attempt to inspire the computer to create art by reading a novel using linguistic programming, extracting its concepts, and then transforming those concepts into photos and shapes.


90 views