Fooling Polarization-Based Vision Using Locally Controllable Polarizing Projection
Zhuoxiao Li, Zhihang Zhong, Shohei Nobuhara, Ko Nishino, Yinqiang Zheng
摘要
Polarization is a fundamental property of light that encodes abundant information regarding surface shape, material, illumination and viewing geometry. The computer vision community has witnessed a blossom of polarizationbased vision applications, such as reflection removal, shape-from-polarization (SfP), transparent object segmentation and color constancy, partially due to the emergence of single-chip mono/color polarization sensors that make polarization data acquisition easier than ever. However, is polarization-based vision vulnerable to adversarial attacks? If so, is that possible to realize these adversarial attacks in the physical world, without being perceived by human eyes? In this paper, we warn the community of the vulnerability of polarization-based vision, which can be more serious than RGB-based vision. By adapting a commercial LCD projector, we achieve locally controllable polarizing projection, which is successfully utilized to fool state-of-theart polarization-based vision algorithms for glass segmentation and SfP. Compared with existing physical attacks on RGB-based vision, which always suffer from the trade-off between attack efficacy and eye conceivability, the adversarial attackers based on polarizing projection are contactfree and visually imperceptible, since naked human eyes can rarely perceive the difference of viciously manipulated polarizing light and ordinary illumination. This poses unprecedented risks on polarization-based vision, for which due attentions should be paid and counter measures be considered.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper12
- Towards Evaluating the Robustness of Neural NetworksNicholas Carlini, David A. WagnerS&P 2017 · 被引用 9,786 次
- Accessorize to a Crime: Real and Stealthy Attacks on State-of-the-Art Face RecognitionMahmood Sharif, Sruti Bhagavatula, Lujo Bauer, Michael K. ReiterCCS 2016 · 被引用 1,765 次
- Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural PhenomenonYiqi Zhong, Xianming Liu, Deming Zhai, Junjun Jiang 等CVPR 2022 · 被引用 148 次
- Glass Segmentation using Intensity and Spectral Polarization CuesHaiyang Mei, Bo Dong, Wen Dong, Jiaxi Yang 等CVPR 2022 · 被引用 91 次
- Shape from Polarization for Complex Scenes in the WildChenyang Lei, Chenyang Qi, Jiaxin Xie, Na Fan 等CVPR 2022 · 被引用 60 次
相关 Paper
- Degree-of-linear-polarization-based Color ConstancyTaishi Ono, Yuhi Kondo, Legong Sun, Teppei Kurita 等CVPR 2022 · 被引用 23 次
- SPIDeRS: Structured Polarization for Invisible Depth and Reflectance SensingTomoki Ichikawa, Shohei Nobuhara, Ko NishinoCVPR 2024
- Polarization State Tracing for Reflection Removal and Color-Consistent ReconstructionDongyue Wang, Yang Lu, Jiandong TianCVPR 2026
- Deep Polarization Cues for Transparent Object SegmentationAgastya Kalra, Vage Taamazyan, Supreeth Krishna Rao, Kartik Venkataraman 等CVPR 2020
- PolarDepth: Monocular Transparent Object Depth from Polar-Physics PriorsWen Dong, Haiyang Mei, Yinglian Ji, Zijun Zhang 等ICML 2026
