Physically Realizable Natural-Looking Clothing Textures Evade Person Detectors via 3D Modeling

TL;DR

This paper introduces AdvCaT, a method for creating natural-looking, adversarial clothing textures using 3D modeling and camouflage patterns to evade person detectors across multiple viewing angles.

Contribution

It proposes a novel approach combining Voronoi diagrams, Gumbel-softmax, and 3D modeling to generate realistic adversarial clothing textures that are effective in real-world scenarios.

Findings

High attack success rates against multiple detectors

Textures are natural-looking and resemble daily clothing

Effective across various viewing angles

Abstract

Recent works have proposed to craft adversarial clothes for evading person detectors, while they are either only effective at limited viewing angles or very conspicuous to humans. We aim to craft adversarial texture for clothes based on 3D modeling, an idea that has been used to craft rigid adversarial objects such as a 3D-printed turtle. Unlike rigid objects, humans and clothes are non-rigid, leading to difficulties in physical realization. In order to craft natural-looking adversarial clothes that can evade person detectors at multiple viewing angles, we propose adversarial camouflage textures (AdvCaT) that resemble one kind of the typical textures of daily clothes, camouflage textures. We leverage the Voronoi diagram and Gumbel-softmax trick to parameterize the camouflage textures and optimize the parameters via 3D modeling. Moreover, we propose an efficient augmentation pipeline on 3D meshes combining topologically plausible projection (TopoProj) and Thin Plate Spline (TPS) to narrow the gap between digital and real-world objects. We printed the developed 3D texture pieces on fabric materials and tailored them into T-shirts and trousers. Experiments show high attack success rates of these clothes against multiple detectors.