“We developed a deep neural network that maps the phase and amplitude of WiFi signals to UV coordinates within 24 human regions. The results of the study reveal that our model can estimate the dense pose of multiple subjects, with comparable performance to image-based approaches, by utilizing WiFi signals as the only input.”
MIT used a high speed camera to reconstruct sound vibrations from objects behind soundproof glass, such as a bag of chips, water in a glass, and a plant. That was in 2014.
https://news.mit.edu/2014/algorithm-recovers-speech-from-vibrations-0804