New Microsoft Research Project Is Trying To Convert Normal 2D Cameras Into Depth Cameras

At SIGGRAPH 2014, the 41st International Conference and Exhibition on Computer Graphics and Interactive Techniques, which starts today in Vancouver, British Columbia, Microsoft Research team is presenting many new projects. In the morning, we reported about the project that which can convert GoPro camera videos into beautiful smooth time-lapse videos called Hyperlapse videos. In this project, MSR is trying to make cheap depth camera by using the regular 2D camera which are found on mobile devices and webcams. After minor modifications, this camera can be used for interactive scenarios. Watch the video above for more.

Among Microsoft Research’s contributions to SIGGRAPH 2014, a machine learning technique for estimating absolute, per-pixel depth using any conventional monocular 2D camera, with minor hardware modifications. Our approach targets close-range human capture and interaction where dense 3D estimation of hands and faces is desired. We use hybrid classification-regression forests to learn how to map from near infrared intensity images to absolute, metric depth in real-time. We demonstrate a variety of humancomputer interaction and capture scenarios. Experiments show an accuracy that outperforms a conventional light fall-off baseline, and is comparable to high-quality consumer depth cameras, but with a dramatically reduced cost, power consumption, and form-factor.

Learn more about it here.

Some links in the article may not be viewable as you are using an AdBlocker. Please add us to your whitelist to enable the website to function properly.