Introduces a differentiable Fourier coefficient representation for generating robust physical adversarial shapes that evade infrared object detectors with over 88% success at long range.
Physically realizable natural-looking clothing textures evade person detectors via 3d modeling
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Unleashing the Representational Power of Fourier Shapes for Attacking Infrared Object Detection
Introduces a differentiable Fourier coefficient representation for generating robust physical adversarial shapes that evade infrared object detectors with over 88% success at long range.