CVPR 2024 to Showcase AI Art Gallery, Feature Prominent AI Artist Sofia Crespo as Keynote

Works explore the intersection of art and science

LOS ALAMITOS, Calif., May 30, 2024 /PRNewswire/ -- As the preeminent event for research and development (R&D) in the hot topic areas of computer vision, artificial intelligence (AI), machine learning (ML), augmented, virtual and mixed reality (AR/VR/MR), deep learning, and related fields, the Computer Vision and Pattern Recognition (CVPR) Conference historically has not been a gathering point for the artistic community, but this year, that will change. Occurring 17-21 June at the Seattle Convention Center in Seattle, Wash., U.S.A., CVPR will feature an AI Art Gallery, curating 68 works that merge science and art, and welcome Sofia Crespo, an artist who explores organic life and its evolution through artificial intelligence, as a keynote speaker.

"Artists work with AI in many different ways," said Luba Elliott, CVPR 2024 Art Curator. "By developing new techniques to create unique aesthetics or using art to explore AI, these featured works offer new expressions of the world around us, demonstrating that science and art are not distinct, but rather intertwined elements of society."

Co-sponsored by the IEEE Computer Society (CS) and the Computer Vision Foundation (CVF), CVPR received 346 submissions for the AI Art Gallery this year, of which fewer than 20% were accepted to be presented in person at the conference. Of these, sample highlights include:

• "Because of You" – Henrietta Lacks is known as "immortal" for a reason – though she died of cervical cancer at age 30, scientists have used her remarkable cells countless times since. HeLa cells, that never stop dividing and hence are functionally immortal, have played a role in some of the most important medical advancements of our time. However, the original cells that started the immortal HeLa cell line were taken from her without her consent or the awareness of her family.
  
  Inspired by this cautionary tale about the dangers of cutting out human creators in the pursuit of technology and a lesson in ethics, privacy, and consent in technological progress, "Because of You" is a digital video work that takes an AI-generated image of Henrietta Lacks and activates it into video by extrapolating frames of movement from one frame to the next. In a sense, it envisions the training of a diffusion model as an in-between place: between information, contributed by humans, and the complete stripping away of that information, which is an aspect of AI model training.
  
  
• "Cycles" – In this video work, face-detecting augmented reality applications are used on a collection of the artist's own selfies, face-swapping and rephotographing these images on screens. Then, a custom machine learning model is trained on these distorted faces such that it can produce new faces based on this influence. Another custom ML model is trained to interpret input body images to be constructed out of the faces from the first model. "Cycles" shows the body in defiance of philosophies and technologies that insist it be a clear, stable, isolated thing. It will be shown as part of a four-screen installation from this artist.
  
  
• "ReCollection" – Born from the artist's experience with his grandmother's memory regression due to dementia, this installation integrates AI systems and experimental visualization into the design of an interactive art experience. "ReCollection" invites participants to share their personal memories in one sentence. The AI system then transforms speech to text and automatically fills in details as a completed narrative, generating new visual memories.

These and 65 other works will be featured in an onsite gallery at the conference. The CVPR AI Art Gallery will be open to the public Wednesday, 19 June through Friday, 21 June from 10:30 a.m. to 6:45 p.m. PDT. A one-day exhibit pass will be available onsite, and guided tours will also be available on Wednesday and Thursday at 11 a.m. and 5 p.m. PDT and Friday at 11 a.m. PDT only. Cash prizes for the best artworks will be awarded on Thursday, 20 June.

In addition, to accommodate the vast number of stellar submissions, CVPR also will offer a virtual exhibition that includes the works displayed onsite, as well as an extra 53 pieces curated for their thematic roles and importance. The gallery will be available online at https://art.thecvf.com, starting 17 June. 

"I've been curating AI art for close to a decade now, and this open call has received the most submissions from artists, scientists, filmmakers, and designers," noted Elliott. "As the technology becomes more mature, accessible, and examinable, an increasing number of artists from different backgrounds are engaging with it to realize their creative visions and probe its limitations."

The intersection of art and AI presents a new paradigm that fuses science and creativity. In fact, a study published in the March 2024 issue of PNAS Nexus, a journal of the National Academy of Sciences of the United States of America, found that "over time, text-to-image AI significantly enhances human creative productivity by 25% and increases the value as measured by the likelihood of receiving a favorite per view by 50%." It goes on to conclude that this new dynamic introduces, "'generative synesthesia'—the harmonious blending of human exploration and AI exploitation to discover new creative workflows."

In addition to the gallery, artist Sofia Crespo, whose work focuses on the way organic life uses artificial mechanisms to simulate itself and evolve, will deliver a keynote address on Friday, 21 June, at 3 p.m. PDT. Crespo will discuss the similarities between techniques of AI image formation and the way that humans express themselves creatively and cognitively recognize their world.

To register for CVPR 2024 as a member of the press and/or request more information on the AI Art Gallery, visit https://cvpr.thecvf.com/Conferences/2024/MediaPass or email [email protected]. For more information on the conference, visit https://cvpr.thecvf.com/. 

About CVPR 2024
The Computer Vision and Pattern Recognition Conference (CVPR) is the preeminent computer vision event for new research in support of artificial intelligence (AI), machine learning (ML), augmented, virtual and mixed reality (AR/VR/MR), deep learning, and much more. Sponsored by the IEEE Computer Society (CS) and the Computer Vision Foundation (CVF), CVPR delivers the important advances in all areas of computer vision and pattern recognition and the various fields and industries they impact. With a first-in-class technical program, including tutorials and workshops, a leading-edge expo, and robust networking opportunities, CVPR, which is annually attended by more than 10,000 scientists and engineers, creates a one-of-a-kind opportunity for networking, recruiting, inspiration, and motivation.

CVPR 2024 takes place 17-21 June at the Seattle Convention Center in Seattle, Wash., U.S.A., and participants may also access sessions virtually. For more information about CVPR 2024, visit cvpr.thecvf.com.

About the Computer Vision Foundation
The Computer Vision Foundation (CVF) is a non-profit organization whose purpose is to foster and support research on all aspects of computer vision. Together with the IEEE Computer Society, it co-sponsors the two largest computer vision conferences, CVPR and the International Conference on Computer Vision (ICCV). Visit thecvf.com for more information.

About the IEEE Computer Society
Engaging computer engineers, scientists, academia, and industry professionals from all areas and levels of computing, the IEEE Computer Society (CS) serves as the world's largest and most established professional organization of its type. IEEE CS sets the standard for the education and engagement that fuels continued global technological advancement. Through conferences, publications, and programs that inspire dialogue, debate, and collaboration, IEEE CS empowers, shapes, and guides the future of not only its 375,000+ community members, but the greater industry, enabling new opportunities to better serve our world. Visit computer.org for more information.

SOURCE IEEE Computer Society