We design a compact but effective CNN model for optical flow by exploiting the well-known design principles: pyramid, warping, and cost volume. Cast in a learnable feature pyramid, our network uses the current optical flow estimate to warp the CNN features of the second image. It then uses the warped features and features of the first image to construct the cost volume, which is processed by a ...

The assessment of regional heart wall motion (local strain) can localize ischemic myocardial disease, evaluate myocardial viability, and identify impaired cardiac function due to hypertrophic or dilated cardiomyopathies. The objectives of this research were to develop and validate a technique known as hyperelastic warping for the measurement of local strains in the left ventricle from clinical ...

We propose a novel method of modeling high quality 3D model in shape and appearance by aligning multiple view range images obtained by a range scanner and multiple view color images taken by a high-resolution color camera around the object. In the proposed method, we achieve accurate registration of range images by using texture consistency of the high-resolution color images. Our registration ...

Image retargeting aims to resize an image to one with a prescribed aspect ratio. Simple scaling inevitably introduces unnatural geometric distortions on the important content of the image. In this paper, we propose a simple and yet effective method to resize an image, which preserves the geometry of the important content, using the Beltrami representation. Our algorithm allows users to interact...

We demonstrate that, for a large class of reflectance functions, there is a direct relationship between image warps and the corresponding geometric deformations of the underlying three-dimensional objects. This helps explain the hidden geometrical assumptions in object recognition schemes which involve two-dimensional image warping computed by matching image intensity. In addition, it allows us...