In this paper we present a novel algorithm for reconstructing 3D scenes from a set of images. The user defines a set of polygonal regions with corresponding labels in each image ...
Remo Ziegler, Wojciech Matusik, Hanspeter Pfister,...
We present a two-layer hierarchical formulation to exploit different levels of contextual information in images for robust classification. Each layer is modeled as a conditional f...
The problem we consider in this paper is to take a single two-dimensional image containing a human figure, locate the joint positions, and use these to estimate the body configura...
We describe a novel method for real-time, simultaneous multi-view face detection and facial pose estimation. The method employs a convolutional network to map face images to point...
We consider the problem of multi-label, supervised image segmentation when an initial labeling of some pixels is given. In this paper, we propose a new generative image segmentatio...
Tae Hoon Kim (Seoul National University), Kyoung M...