The goal of my research is to enable fully immersive remote communication and interaction in the virtual world at a level that is indistinguishable from reality. One challenge is photo-realistic digitization and efficient rendering of digital humans. I develop key technology that combines fundamental computer vision, machine learning, and graphics techniques in a new neural capture and rendering paradigm. I believe that these novel neural rendering techniques will bring immersive communication in virtual and augmented reality one step closer to reality, and thus completely change the way we communicate in the future.