Fast Preprocessing for Robust Face Sketch Synthesis

TL;DR

This paper introduces a fast preprocessing technique called Bidirectional Luminance Remapping (BLR) that enhances the robustness of exemplar-based face sketch synthesis under varying lighting conditions by adjusting image lighting interactively.

Contribution

The paper proposes a novel, efficient preprocessing method that can be integrated into existing face sketch synthesis methods to improve lighting robustness without significant computational overhead.

Findings

BLR improves robustness to lighting variations in face sketch synthesis.

The method is computationally efficient and easy to integrate.

Experimental results show enhanced performance under different lighting conditions.

Abstract

Exemplar-based face sketch synthesis methods usually meet the challenging problem that input photos are captured in different lighting conditions from training photos. The critical step causing the failure is the search of similar patch candidates for an input photo patch. Conventional illumination invariant patch distances are adopted rather than directly relying on pixel intensity difference, but they will fail when local contrast within a patch changes. In this paper, we propose a fast preprocessing method named Bidirectional Luminance Remapping (BLR), which interactively adjust the lighting of training and input photos. Our method can be directly integrated into state-of-the-art exemplar-based methods to improve their robustness with ignorable computational cost.