Learn More
We describe a method for producing a smooth, stabilized video from the shaky input of a hand-held light field video camera—specifically, a small camera array. Traditional stabilization techniques dampen shake with 2D warps, and thus have limited ability to stabilize a significantly shaky camera motion through a 3D scene. Other recent stabilization(More)
We propose a novel formulation of stereo matching that considers each pixel as a feature vector. Under this view, matching two or more images can be cast as matching point clouds in feature space. We build a nonparametric depth smoothness model in this space that correlates the image features and depth values. This model induces a sparse graph that links(More)
We propose a data-driven approach to facial landmark localization that models the correlations between each landmark and its surrounding appearance features. At runtime, each feature casts a weighted vote to predict landmark locations, where the weight is precomputed to take into account the feature's discriminative power. The feature voting-based landmark(More)
In this paper, we present a new framework for non-rigid structure from motion (NRSFM) that simultaneously addresses three significant challenges: severe occlusion, perspective camera projection, and large non-linear deformation. We introduce a concept called a model graph, which greatly reduces the computational cost of discovering groups of input images(More)
In this work, we propose an exemplar-based face image segmentation algorithm. We take inspiration from previous works on image parsing for general scenes. Our approach assumes a database of exemplar face images, each of which is associated with a hand-labeled segmentation map. Given a test image, our algorithm first selects a subset of exemplar images from(More)
In this paper we make the first effort, to the best of our knowledge, to combine multiple face landmark datasets with different landmark definitions into a super dataset, with a union of all landmark types computed in each image as output. Our approach is flexible, and our system can optionally use known landmarks in the target dataset to constrain the(More)
Figures 1 and 2 supplement Figure 4 in our paper. In all cases, the input images come from our Helen [1] test set. We note that our algorithm generally produces accurate results, as shown in Figures 1. However, our algorithm is not perfect and makes mistakes on especially challenging input images, as shown in Figure 2. In our view, the mouth is the most(More)