The Making and Breaking of Camouflage

TL;DR

This paper introduces quantitative scores for evaluating camouflage effectiveness, uses these scores to analyze datasets, and develops a generative model to synthesize camouflaged images, enhancing segmentation performance and achieving state-of-the-art results.

Contribution

It proposes novel camouflage effectiveness scores, integrates them into a generative model, and improves camouflaged animal segmentation with synthetic data.

Findings

Camouflage scores correlate with visibility and boundary features.

Synthetic datasets improve segmentation accuracy.

Achieves state-of-the-art performance on MoCA-Mask benchmark.

Abstract

Not all camouflages are equally effective, as even a partially visible contour or a slight color difference can make the animal stand out and break its camouflage. In this paper, we address the question of what makes a camouflage successful, by proposing three scores for automatically assessing its effectiveness. In particular, we show that camouflage can be measured by the similarity between background and foreground features and boundary visibility. We use these camouflage scores to assess and compare all available camouflage datasets. We also incorporate the proposed camouflage score into a generative model as an auxiliary loss and show that effective camouflage images or videos can be synthesised in a scalable manner. The generated synthetic dataset is used to train a transformer-based model for segmenting camouflaged animals in videos. Experimentally, we demonstrate state-of-the-art camouflage breaking performance on the public MoCA-Mask benchmark.