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.
@article{arxiv.2410.04789,
title = {Analysis of Hybrid Compositions in Animation Film with Weakly Supervised Learning},
author = {Mónica Apellaniz Portos and Roberto Labadie-Tamayo and Claudius Stemmler and Erwin Feyersinger and Andreas Babic and Franziska Bruckner and Vrääth Öhner and Matthias Zeppelzauer},
journal= {arXiv preprint arXiv:2410.04789},
year = {2024}
}
Comments
Vision for Art (VISART VII) Workshop at the European Conference of Computer Vision (ECCV)