The Making and Breaking of Camouflage
This work addresses the challenge of automatically assessing and generating effective camouflage for applications in computer vision, such as improving segmentation of camouflaged animals, though it is incremental as it builds on existing datasets and methods.
The paper tackled the problem of measuring camouflage effectiveness by proposing three automatic scores based on background-foreground similarity and boundary visibility, and used these scores to generate synthetic camouflage data, achieving state-of-the-art performance on the MoCA-Mask benchmark for segmenting camouflaged animals in videos.
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.