The precise alignment of a 3D model to 2D sensor images to recover the pose of an object in a scene is an important topic in computer vision. In this work, we outline a registrati...
This paper presents a framework to automatically detect and recover the occluded facial region. We first derive a Bayesian formulation unifying the occlusion detection and recover...
We consider the problem of detecting and accounting for the presence of occluders in a 3D scene based on silhouette cues in video streams obtained from multiple, calibrated views....
We present an algorithm for performing Lambertian photometric stereo in the presence of shadows. The algorithm has three novel features. First, a fast graph cuts based method is u...
This paper addresses the problem of generating a superresolution (SR) image from a single low-resolution input image. We approach this problem from the perspective of compressed s...
Jianchao Yang, John Wright, Thomas S. Huang, Yi Ma