Analysis of Hybrid Compositions in Animation Film with Weakly Supervised Learning

TL;DR

This paper introduces a weakly supervised learning method for analyzing hybrid visual compositions in animation films, enabling segmentation without labeled data and providing new insights into animation techniques.

Contribution

It presents a novel semi-supervised approach for segmenting hybrid compositions in animation without needing pre-labeled masks.

Findings

Performance close to fully supervised methods

Effective segmentation of hybrid compositions

Provides qualitative insights into animation techniques

Abstract

We present an approach for the analysis of hybrid visual compositions in animation in the domain of ephemeral film. We combine ideas from semi-supervised and weakly supervised learning to train a model that can segment hybrid compositions without requiring pre-labeled segmentation masks. We evaluate our approach on a set of ephemeral films from 13 film archives. Results demonstrate that the proposed learning strategy yields a performance close to a fully supervised baseline. On a qualitative level the performed analysis provides interesting insights on hybrid compositions in animation film.