Justin Johnson

Justin Johnson is an Assistant Professor at the University of Michigan and a Research Scientist at Facebook AI Research (FAIR). His work spans computer vision and machine learning, with a focus on visual reasoning, vision-and-language integration, image generation, and 3D reasoning through deep neural networks.

• Education: PhD from Stanford University under Fei-Fei Li

His research combines visual reasoning and 3D reconstruction with applications in image generation and neural rendering. He has contributed to advancing style transfer, super-resolution, and 3D deep learning through frameworks like PyTorch3D. Recent publications emphasize scalable 3D modeling, neural fields, and vision-language grounding.

He advises PhD students including Karan Desai, Mohamed El Banani, and Chris Rockwell (co-advised with David Fouhey). He has taught courses like EECS 498/598: Deep Learning for Computer Vision at Michigan and CS 231N: Convolutional Neural Networks for Visual Recognition at Stanford.