In a study published today in Physical Review Letters, the researchers reconstructed transparent objects from images of those objects, taken in almost pitch-black conditions.

They did so using depth camera images of opaque objects paired with color images of those same objects. Once trained, the color camera system was applied to transparent and shiny objects.

The photographed reference images would serve as input, while the CT scans would provide reference surface geometry of the glass objects, Frisvad noted, providing a testbed for developing vision ...

A new imaging technique makes it possible to precisely digitize clear objects and their surroundings, an achievement that has eluded current state-of-the-art 3-D rendering methods.

ClearGrasp, a new Google-developed AI model, helps autonomous robot arms to grasp objects that are transparent in appearance.

A Caltech researcher has developed a groundbreaking camera capable of capturing up to 1 trillion frames per second—fast enough to reveal the inner workings of transparent objects once thought ...

Processing begins. In addition, since "Creating a transparent image with object recognition cutout" supports GPU support, images can be processed with little time when discrete GPUs are used.

Conventional systems fail on transparent or dark objects because they distort or absorb light. goROBOT3D gets around this by using structured thermal imaging. It projects heat patterns onto a surface ...

The team trained the network to look for transparent patterns in dark images by feeding it 10,000 purposefully dark, grainy and out-of-focus pictures as well as the patterns those pictures are ...

It’s certainly not easy, but a new camera can do just that. Developed by Caltech engineer Lihong Wang, the camera takes an impressive trillion pictures per second of transparent objects.