GAMES Webinar 2023 – 276期(GigaGAN在文本生成图像的应用) | Taesung Park (Adobe Inc.)

【GAMES Webinar 2023-276期】(视觉专题-GigaGAN在文本生成图像的应用)

报告嘉宾:Taesung Park (Adobe Inc.)


报告题目:Scaling-Up GANs for Text-to-Image Synthesis


The quality of AI-generated images has drastically improved in recent years. The advancement was largely driven by the success of training diffusion-based models on large-scale Internet datasets. The phenomenon begs the question, what happened to GAN-based models? GANs served as the de-facto image synthesis model for many years. In this talk, we investigate if GANs can also be scaled up for large-scale training, and discuss the potential advantages of leveraging GAN models.


Taesung is a Research Scientist at Adobe Research, focusing on image editing using generative models. He is a core contributor to Adobe Firefly, a text-to-image generative model that is faster in generating high-resolution images and trained on ethically sourced data. He received Ph.D. in Computer Science at UC Berkeley, advised by Prof. Alexei Efros. Previously he interned at Adobe in 2019, working with Richard Zhang, and at NVIDIA, working with Ming-Yu Liu in the summer of 2018. He received B.S. in Mathematics and M.S. in Computer Science, both at Stanford University.



Jun-Yan Zhu is an Assistant Professor in the School of Computer Science at CMU. Prior to joining CMU, he was a Research Scientist at Adobe and a postdoc at MIT CSAIL. He obtained his Ph.D. from UC Berkeley and B.E. from Tsinghua University. He studies computer vision, computer graphics, and computational photography. His current research focuses on studying the interaction between human creators and large-scale generative models.


GAMES主页的“使用教程”中有 “如何观看GAMES Webinar直播?”及“如何加入GAMES微信群?”的信息;

You may also like...