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...
This paper proposes a new interactive hybrid non-rigid registration framework that combines any intensity-based algorithm with a feature-based component, using an iterative dual e...
Antoine Azar, Chenyang Xu, Xavier Pennec, Nicholas...
We present an approach to low-level vision that combines two main ideas: the use of convolutional networks as an image processing architecture and an unsupervised learning procedu...
In this paper, we wish to build a high quality database of
images depicting scenes, along with their real-world threedimensional
(3D) coordinates. Such a database is useful
for ...
Abstract. Accurate signal recovery or image reconstruction from indirect and possibly undersampled data is a topic of considerable interest; for example, the literature in the rece...