Estimating Image Depth in the Comics Domain

TL;DR

This paper presents a novel method for estimating depth in comic images by translating them to natural images and applying a monocular depth estimator, outperforming existing methods and introducing a new evaluation dataset.

Contribution

The authors propose an innovative approach combining image translation and attention-guided depth estimation for comics, along with a new dataset for evaluation.

Findings

Outperforms state-of-the-art methods on DCM and eBDtheque datasets.

Effectively distinguishes text from images to improve depth accuracy.

Provides a new dataset for depth evaluation in comics.

Abstract

Estimating the depth of comics images is challenging as such images a) are monocular; b) lack ground-truth depth annotations; c) differ across different artistic styles; d) are sparse and noisy. We thus, use an off-the-shelf unsupervised image to image translation method to translate the comics images to natural ones and then use an attention-guided monocular depth estimator to predict their depth. This lets us leverage the depth annotations of existing natural images to train the depth estimator. Furthermore, our model learns to distinguish between text and images in the comics panels to reduce text-based artefacts in the depth estimates. Our method consistently outperforms the existing state-ofthe-art approaches across all metrics on both the DCM and eBDtheque images. Finally, we introduce a dataset to evaluate depth prediction on comics. Our project website can be accessed at https://github.com/IVRL/ComicsDepth.