Computer Vision
Enabling computers and devices to understand what they see.
Video
Real-Time Face Reconstruction from a Single Depth Image
This paper contributes a real time method for recovering facial shape and expression from a single depth image. The method also estimates an accurate and dense correspondence field between the input depth image and a…
Publication
Touchless interaction in surgical settings
Tool
Sparse Reflections Analysis: Sensor Data from ECCV 2014 Paper
This file contains the raw sensor data used the ECCV 2014 paper, “SRA: Fast Removal of General Multipath for ToF Sensors” by D. Freedman, Y. Smolin, E. Krupka, I. Leichter, and M. Schmidt. This includes…
Video
Appearance-from-Motion: Recovering Spatially Varying Surface Reflectance under Unknown Lighting
We present “appearance-from-motion”, a novel method for recovering the spatially varying isotropic surface reflectance from a video of a rotating subject, with known geometry, under unknown natural illumination. We formulate the appearance recovery as an…
Video
Automatic Acquisition of High-fidelity Facial Performances Using Monocular Videos
This paper presents a facial performance capture system that automatically captures high-fidelity facial performances using uncontrolled monocular videos (e.g., Internet videos). We start the process by detecting and tracking important facial features such as the…
Microsoft Research Blog
Fitzgibbon Channels Led Zeppelin into Practical Engineering
When it comes to research, the concept of “head-banging” most likely conjures images of researchers banging their heads against walls or dry-erase boards. But for Microsoft researcher Andrew Fitzgibbon, it’s about inspiration. “I was on…