Models trained on synthetic data can be more accurate than other models in some cases, which could eliminate some privacy, copyright, and ethical concerns from using real data.

MIT researchers have developed a machine-learning technique that accurately captures and models the underlying acoustics of a scene from only a limited number of sound recordings. In this image, a sound emitter is marked by a red dot. The colors show the sound volume if a listener were to stand at different locations — yellow is louder and blue is quieter.

Yilun Du, a PhD student and MIT CSAIL affiliate, discusses the potential applications of generative art beyond the explosion of images that put the web into creative hysterics.

MuscleRehab is a system that uses electrical impedance tomography and optical motion tracking for visualizing muscle engagement and motion data during unsupervised physical rehabilitation.

Researchers develop a new method that uses multiple models to create more complex images with better understanding.

Inspired by a fiddler crab eye, scientists developed an amphibious artificial vision system with a panoramic visual field.

Caption:

MIT researchers have trained a machine-learning model to monitor and adjust the 3D printing process in real-time.

MIT researchers create KineCAM, an instant camera that yields images that appear to move.

Caption:

Researchers created a computer vision system that combines two types of correspondences for accurate pose estimation across a wide range of scenarios to "see-through" scenes.

Researchers have created prototypes that enable screen-reader users to quickly and easily navigate through multiple levels of information in an online chart.