Guiding Users to Where to Give Color Hints for Efficient Interactive Sketch Colorization via Unsupervised Region Prioritization

TL;DR

This paper introduces GuidingPainter, a model-guided framework that actively identifies key regions for user color hints in sketch colorization, reducing user effort and improving results.

Contribution

It presents a novel region prioritization approach that guides users on where to give hints, enhancing interactive colorization efficiency.

Findings

Outperforms existing methods in PSNR and FID metrics.

Reduces the number of user interactions needed.

Demonstrates effectiveness across diverse sketches.

Abstract

Existing deep interactive colorization models have focused on ways to utilize various types of interactions, such as point-wise color hints, scribbles, or natural-language texts, as methods to reflect a user's intent at runtime. However, another approach, which actively informs the user of the most effective regions to give hints for sketch image colorization, has been under-explored. This paper proposes a novel model-guided deep interactive colorization framework that reduces the required amount of user interactions, by prioritizing the regions in a colorization model. Our method, called GuidingPainter, prioritizes these regions where the model most needs a color hint, rather than just relying on the user's manual decision on where to give a color hint. In our extensive experiments, we show that our approach outperforms existing interactive colorization methods in terms of the conventional metrics, such as PSNR and FID, and reduces required amount of interactions.