SketchPatch: Sketch Stylization via Seamless Patch-level Synthesis

TL;DR

SketchPatch introduces a patch-level image translation approach for sketch stylization, effectively handling limited data and ensuring seamless style transfer without artifacts through a novel hybrid input and adversarial training.

Contribution

The paper proposes a new patch-level translation method with hybrid inputs and adversarial training to achieve seamless sketch stylization with limited data.

Findings

Effective stylization across various styles and sketches

Seamless patch synthesis reduces border artifacts

Robust generalization to diverse geometries

Abstract

The paradigm of image-to-image translation is leveraged for the benefit of sketch stylization via transfer of geometric textural details. Lacking the necessary volumes of data for standard training of translation systems, we advocate for operation at the patch level, where a handful of stylized sketches provide ample mining potential for patches featuring basic geometric primitives. Operating at the patch level necessitates special consideration of full sketch translation, as individual translation of patches with no regard to neighbors is likely to produce visible seams and artifacts at patch borders. Aligned pairs of styled and plain primitives are combined to form input hybrids containing styled elements around the border and plain elements within, and given as input to a seamless translation (ST) generator, whose output patches are expected to reconstruct the fully styled patch. An adversarial addition promotes generalization and robustness to diverse geometries at inference time, forming a simple and effective system for arbitrary sketch stylization, as demonstrated upon a variety of styles and sketches.