KEPLER: Simultaneous estimation of keypoints and 3D pose of unconstrained faces in a unified framework by learning efficient H-CNN regressors
Image Vision Comput., Volume 79, 2018, Pages 49-62.
Abstract Keypoint detection is one of the most important pre-processing steps in tasks such as face modeling, recognition and verification. In this paper, we present an iterative method for Keypoint Estimation and Pose prediction of unconstrained faces by Learning Efficient H-CNN Regressors (KEPLER) for addressing the unconstrained face...More
Full Text (Upload PDF)
PPT (Upload PPT)