Improving Sketch Colorization using Adversarial Segmentation Consistency

TL;DR

This paper introduces a novel adversarial segmentation consistency loss for sketch colorization, enhancing GAN-based models to produce more accurate and diverse color images from sketches without requiring paired datasets.

Contribution

It presents a segmentation-based adversarial loss compatible with any GAN, enabling unpaired sketch colorization and improving results significantly.

Findings

Up to 35-point improvement in FID scores

Effective on four diverse datasets

Applicable to unpaired translation tasks

Abstract

We propose a new method for producing color images from sketches. Current solutions in sketch colorization either necessitate additional user instruction or are restricted to the "paired" translation strategy. We leverage semantic image segmentation from a general-purpose panoptic segmentation network to generate an additional adversarial loss function. The proposed loss function is compatible with any GAN model. Our method is not restricted to datasets with segmentation labels and can be applied to unpaired translation tasks as well. Using qualitative, and quantitative analysis, and based on a user study, we demonstrate the efficacy of our method on four distinct image datasets. On the FID metric, our model improves the baseline by up to 35 points. Our code, pretrained models, scripts to produce newly introduced datasets and corresponding sketch images are available at https://github.com/giddyyupp/AdvSegLoss.