{"id":206,"date":"2020-09-12T16:01:32","date_gmt":"2020-09-12T16:01:32","guid":{"rendered":"https:\/\/machine-learning.webcloning.com\/2020\/09\/12\/perfect-pairing-nvidias-david-luebke-on-the-intersection-of-ai-and-graphics\/"},"modified":"2020-09-12T16:01:32","modified_gmt":"2020-09-12T16:01:32","slug":"perfect-pairing-nvidias-david-luebke-on-the-intersection-of-ai-and-graphics","status":"publish","type":"post","link":"https:\/\/salarydistribution.com\/machine-learning\/2020\/09\/12\/perfect-pairing-nvidias-david-luebke-on-the-intersection-of-ai-and-graphics\/","title":{"rendered":"Perfect Pairing: NVIDIA\u2019s David Luebke on the Intersection of AI and Graphics"},"content":{"rendered":"
\n

NVIDIA Research<\/a> comprises more than 200 scientists around the world driving innovation across a range of industries. One of its central figures is David Luebke, who founded the team in 2006 and is now the company\u2019s vice president of graphics research.<\/p>\n

Luebke spoke with AI Podcast<\/a> host Noah Kravitz about what he\u2019s working on. He\u2019s especially focused on the interaction between AI and graphics. Rather than viewing the two as conflicting endeavors, Luebke argues that AI and graphics go together \u201clike peanut butter and jelly.\u201d<\/p>\n

NVIDIA Research proved that with StyleGAN2<\/a>, the second iteration of the generative adversarial network<\/a> StyleGAN. Trained on high-resolution images, StyleGAN2 takes numerical input and produces realistic portraits.<\/p>\n

Creating images comparable to those generated in films \u2014 which could take up to weeks to create just a single frame \u2014 the first version of StyleGAN only takes 24 milliseconds to produce an image.<\/p>\n

Luebke envisions the future of GANs as an even larger collaboration between AI and graphics. He predicts that GANs such as those used in StyleGAN will learn to produce the key elements of graphics: shapes, materials, illumination and even animation.<\/p>\n

Key Points From This Episode:<\/b><\/h2>\n