My research focuses on machine learning approaches to understanding and analyzing digital images and videos. My lab and I develop new deep learning models and methods for scene understanding, motion estimation, image editing and synthesis, video analysis, image restoration, and more. We aim to make such approaches robust to a broad range of real-world conditions. To that end, we are incorporating inductive biases through combining deep learning with classical models, endowing deep networks with explicit representations of uncertainty, or adapting pre-trained models to changing test-time circumstances. We also aim to reduce the dependency on labeled data by developing semi-supervised and self-supervised learning pipelines.