![]() ![]() The power of these models has rocked industry and users alike. “There are a lot of techniques that were initially invented by physicists and now are very important in machine learning,” said Yang Song, a machine-learning researcher at OpenAI. The system that underpins them, known as a diffusion model, is heavily inspired by nonequilibrium thermodynamics, which governs phenomena like the spread of fluids and gases. The key insight that makes DALL♾ 2’s images possible-as well as those of its competitors Stable Diffusion and Imagen-comes from the world of physics. Meanwhile, a powerful generative model-created by a postdoctoral researcher with a passion for physics-lay dormant, until two graduate students made technical breakthroughs that brought the beast to life.ĭALL♾ 2 is such a beast. But even as the quality of their images got better, the models proved unreliable and hard to train. The first important generative models for images used an approach to artificial intelligence called a neural network-a program composed of many layers of computational units called artificial neurons. This is one of the hardest problems in machine learning, and getting to this point has been a difficult journey. ![]() This was integrated with Notch for visual effects and LightAct and Disguise for video projection on the floor and walls.Original story reprinted with permission from Quanta Magazine, an editorially independent publication of the Simons Foundation whose mission is to enhance public understanding of science by covering research developments and trends in mathematics and the physical and life sciences.ĭALL♾ 2 is a type of generative model-a system that attempts to use training data to generate something new that’s comparable to the data in terms of quality and variety. The movements of the acrobatic dancers were captured with an infrared camera at ground level, the dance floor becoming the canvas on which their bodies paint the picture.Īugmenta cameras were used to capture the movements of the spectators in an immersive exhibition context. This lab allowed us to explore these creations in physical conditions very similar to the exhibition space. The goal is to immerse visitors in interpretations that they can play with for a more direct, emotional, and artistic link with complex scientific concepts. They can move around, and their movements have an impact on these representations. The second project is an immersive and interactive exhibit created Supply & Demand for the TELUS Spark Science Centre in Calgary, in collaboration with our partner Eden Creative Studios.įive major concepts of quantum physics are represented through artistic visuals, in which spectators are immersed. Quantum for the TELUS Spark Science Center In the interactive piece, movements are transformed in real time into a virtual artwork reminiscent of Riopelle’s style, with strokes of color evoking Riopelle’s use of a spatula to apply paint (artist: Charles-Alexis Desgagnés). Dance All Over, an installation inspired by the work of painter Jean-Paul Riopelle, was also presented by LAB7 at MTL Connect. ![]() The technology allowed us to bring together dance and painting, to express the vital energy at the heart of Riopelle’s work.Īt the end of the lab, two acts were presented at the press conference where the Fondation Jean Paul Riopelle announced the centennial celebrations. Little by little, the painting takes shape. The spatula strokes come to life before the eyes of the audience, following the movements of an acrobatic dancer present on stage. This lab is an opportunity to explore the visual universe of the artist, particularly the All-Over period. The 7 Fingers take part in celebrating the 100 th birthday of Quebec painter, printmaker and sculptor Jean Paul Riopelle by creating a show-event in the summer of 2023. On the artistic side, this data was translated into a virtual painting inspired by the work of Jean-Paul Riopelle, and were used to give life to visual interpretations of quantum physics concepts. We used infrared cameras to analyze the steps of an acrobatic dancer, and Augmenta to capture visitors moving around a museum-like space. This second lab hosts two projects exploring non-figurative visual representations based on different types of motion capture. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |