Patch correspondences

Recently, patch-based approaches, such as those of Kanade and Yamada, have taken advantage of this effect resulting in improved viewpoint invariant face recognition. In this paper we propose a data-driven extension to their approach, in which we not only model how a face patch varies in appearance, but also how it deforms spatially as the viewpoint varies.

One can then view the spatial deformation of a patch as the correspondence of that patch between two viewpoints. We present improved identification and verification results to demonstrate the utility of our technique. Article :. DOI: Higher is better for the metric. Uses extra training data. Data evaluated on. Attached tasks:. Add: Create a new task. New task name:. Parent task if any : Homography Estimation - Visual Localization -. Create a new method. New method name e.

ReLU :. New method full name e. Rectified Linear Unit :. Paper where method was first introduced : Method category e. Activation Functions : If no match, add something for now then you can add a new category afterwards. Add or remove datasets introduced in this paper:. Paper introduces a new dataset?

Add a new dataset here. Code Edit Add Remove Mark official. Tasks Edit Add Remove. Homography Estimation Visual Localization. Datasets Edit. Results from the Paper Edit. Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.