Abstract: Deep networks provide state-of-the-art performance in many inverse imaging problems, ranging from medical imaging to computational photography. In several imaging problems, we typically only have access to compressed measurements of the underlying signals, which complicates most learning-based strategies that typically require pairs of signals and associated measurements for training. Learning only from compressed measurements is generally impossible, as the compressed observations do not contain information outside the range of the forward sensing operator. In this talk, I will present a new end-to-end self-supervised framework, called Equivariant Imaging (EI), which overcomes this limitation by exploiting the equivariances present in natural signals. Our proposed learning strategy performs as well as fully supervised methods. Experiments demonstrate the potential of this framework on inverse problems including sparse-view X-ray computed tomography, accelerated MRI, and image inpainting.