A novel manifold preserving edit propagation based on K nearest neighbors and locally linear embedding

Abstract

Manifold preserving edit propagation provides a robust way for propagating sparse user edits to a whole image, which preserves the manifold structure during edit propagation. In this paper, we propose to use k nearest neighbors (KNN) and locally linear embedding (LLE) to perform manifold preserving edit propagation. We make innovations from two aspects. First, KNN is adopted to find the neighbors of the similar features with the sample pixel. Secondly, we represent each pixel as a linear combination of its neighbors in feature space according to LLE. Finally, the image will be reconstructed by using the weights computed according to LLE. We have demonstrated our manifold preserving edit propagation on various applications including matting, colorization and color replacement. The experimental results have proved the effectiveness of the proposed algorithm.