Image
Robotic arm squishes a block of play dough into an x shape
MIT news article

A new system lets robots manipulate soft, deformable material into various shapes from visual inputs, which could one day enable better home assistants.

Image
Computer graphic illustration: At left, a camera peers up through a slanted image representing a photo of a man shooting a basket, while on the other side of the image, a 3D rendering of that man appears. At right: A reflection of this same scene with camera, photo, and human model, but seen from behind.
MIT news article

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.