Action recognition is an important and challenging topic in computer vision, with many important applications including video surveillance, automated cinematography and understand...
— Depth information indicates the distance of an object in the three dimensional (3D) scene from the camera view-point, typically represented by eight bits. Since the depth map i...
From a rectified stereo image pair, the task of view synthesis is to generate images from any viewpoint along the baseline. The main difficulty of the problem is how to fill oc...
Ankit K. Jain, Lam C. Tran, Ramsin Khoshabeh, Truo...
We present a method for retexturing non-rigid objects from a single viewpoint. Without reconstructing 3D geometry, we create realistic video with shape cues at two scales. At a coa...
— This paper presents a parallel algorithm of the Level Set Method named the Parallel Fast Level Set Method, and its application for real-time 3D reconstruction of human shape an...