We propose a novel exemplar based method to estimate 3D human poses from single images by using only the joint correspondences. Due to the inherent depth ambiguity, estimating 3D ...
Recent research in visual inference from monocular images has shown that discriminatively trained image-based predictors can provide fast, automatic qualitative 3D reconstructions...
Atul Kanaujia, Cristian Sminchisescu, Dimitris N. ...
We present an algorithm for jointly learning a consistent bidirectional generative-recognition model that combines top-down and bottom-up processing for monocular 3d human motion ...
Cristian Sminchisescu, Atul Kanaujia, Dimitris N. ...
In recent years, depth cameras have become a widely available sensor type that captures depth images at realtime frame rates. Even though recent approaches have shown that 3D pose...
Andreas Baak, Meinard Muller, Gaurav Bharaj, Hans-...
In this paper we present a technique for predicting the 2D human body joints and limbs position in monocular image sequences, and reconstructing its corresponding 3D postures using...