MoSculp: MIT CSAIL uses AI to create 3D printed 'motion sculptures' from 2D videos

3ders.org | 9/19/2018 | Staff
TitanSwimr (Posted by) Level 3
Click For Photo: https://www.3ders.org/images2018/mosculp-mit-csail-uses-ai-to-create-3d-printed-motion-sculptures-from-2d-videos-1.png




Understanding of movement is fundamental for all living species, regardless of whether it's figuring out what angle to throw a ball at, or seeing the motion of predators and prey. But simple videos can't actually give us the full picture. As traditional videos and photos for studying motion are two-dimensional, they thus don't show us the underlying 3D structure of the person or subject of interest.

Now researchers at the Massachusetts Institute of Technology’s Computer Science and Artificial Intelligence Lab, Google Research, and the University of California Berkley, have come up with an artificially intelligent (AI) system to show how a human body moves.

System - MoSculp - Algorithm - Videos - Motion

The system, dubbed MoSculp, uses an algorithm that can take 2D videos and turn them into 3D printed "motion sculptures." It could enable a much more detailed study of motion for professional athletes, dancers, or anyone who wants to improve their physical skills.

"Imagine you have a video of Roger Federer serving a ball in a tennis match, and a video of yourself learning tennis," says PhD student Xiuming Zhang. "You could then build motion sculptures of both scenarios to compare them and more comprehensively study where you need to improve."

Practice - Video - System - MoSculp - Keypoints

Here’s how it works in practice: After a video’s loaded into the system, MoSculp overlays the detected keypoints on input frames and confirms them with a few randomly selected frames. (A built-in correction tool lets users make adjustments if necessary.) After correcting for “temporally inconsistent detections,” it generates the motion sculpture and loads it into a custom interface.

It is a multistep process and all MoSculp needs is a video sequence. Here’s how it works: After a video’s loaded into the system, MoSculp first automatically detects 2D key points on the subject's body, for example, the hip, knee, and...
(Excerpt) Read more at: 3ders.org
Wake Up To Breaking News!
Sign In or Register to comment.

Welcome to Long Room!

Where The World Finds Its News!