23 papers with code • 1 benchmarks • 1 datasets
LibrariesUse these libraries to find Geometric Matching models and implementations
We address the problem of determining correspondences between two images in agreement with a geometric model such as an affine or thin-plate spline transformation, and estimating its parameters.
Second, to alleviate boundary artifacts of warped clothes and make the results more realistic, we employ a Try-On Module that learns a composition mask to integrate the warped clothes and the rendered image to ensure smoothness.
Establishing dense correspondences between a pair of images is an important and general problem, covering geometric matching, optical flow and semantic correspondences.
We propose GOCor, a fully differentiable dense matching module, acting as a direct replacement to the feature correlation layer.
At the core of the C-VTON pipeline are: (i) a geometric matching procedure that efficiently aligns the target clothing with the pose of the person in the input images, and (ii) a powerful image generator that utilizes various types of contextual information when synthesizing the final try-on result.
While such generic features cannot compete with class specific features from supervised training on a classification task, we show that they are advantageous on geometric matching problems, where they also outperform the SIFT descriptor.
Most existing studies on learning local features focus on the patch-based descriptions of individual keypoints, whereas neglecting the spatial relations established from their keypoint locations.