Dense Multitask Learning to Reconfigure Comics

TL;DR

This paper introduces a multi-task learning model that performs dense predictions on comic panels, enabling automated reconfiguration and transfer of comics across publication channels despite artistic diversity and limited annotations.

Contribution

The paper presents a novel multi-task learning approach with a vision transformer backbone for dense prediction in comics, leveraging unsupervised translation to overcome annotation scarcity.

Findings

Successfully identifies semantic units and 3D notions in comic panels

Enables reconfiguration of comics through integration with retargeting methods

Demonstrates domain transferability across diverse artistic styles

Abstract

In this paper, we develop a MultiTask Learning (MTL) model to achieve dense predictions for comics panels to, in turn, facilitate the transfer of comics from one publication channel to another by assisting authors in the task of reconfiguring their narratives. Our MTL method can successfully identify the semantic units as well as the embedded notion of 3D in comic panels. This is a significantly challenging problem because comics comprise disparate artistic styles, illustrations, layouts, and object scales that depend on the authors creative process. Typically, dense image-based prediction techniques require a large corpus of data. Finding an automated solution for dense prediction in the comics domain, therefore, becomes more difficult with the lack of ground-truth dense annotations for the comics images. To address these challenges, we develop the following solutions: 1) we leverage a commonly-used strategy known as unsupervised image-to-image translation, which allows us to utilize a large corpus of real-world annotations; 2) we utilize the results of the translations to develop our multitasking approach that is based on a vision transformer backbone and a domain transferable attention module; 3) we study the feasibility of integrating our MTL dense-prediction method with an existing retargeting method, thereby reconfiguring comics.