Stylizing Face Images via Multiple Exemplars
This addresses the issue of inaccurate style transfer in face images when using insufficient exemplars, offering an incremental improvement for computer vision applications.
The paper tackles the problem of stylizing face images by transferring style from multiple exemplars instead of a single one, resulting in consistently visually pleasing outputs as shown in experiments.
We address the problem of transferring the style of a headshot photo to face images. Existing methods using a single exemplar lead to inaccurate results when the exemplar does not contain sufficient stylized facial components for a given photo. In this work, we propose an algorithm to stylize face images using multiple exemplars containing different subjects in the same style. Patch correspondences between an input photo and multiple exemplars are established using a Markov Random Field (MRF), which enables accurate local energy transfer via Laplacian stacks. As image patches from multiple exemplars are used, the boundaries of facial components on the target image are inevitably inconsistent. The artifacts are removed by a post-processing step using an edge-preserving filter. Experimental results show that the proposed algorithm consistently produces visually pleasing results.