Teaching

Vision transformer, generative models, neural fields, open vocabulary perception and large vision-language models.

Object detection, semantic segmentation, human pose estimation, face recognition, visual SLAM.

Image formation, photometric vision, geometric vision, neural networks, image classification.

Weekly seminar with invited talks featuring research and exploratory themes in vision, graphics and learning.

Advanced topics in 3D representation, inverse rendering, image generation and applications such as autonomous driving and augmented reality.

Research for PhD thesis, MS thesis, independent studies and undergraduate programs including REU, ENLACE and ERSP.