paper-with-me

Papers

Fooling Polarization-based Vision using Locally Controllable Polarizing Projection

2023-03-31 · CVPR 2024 1 · Zhuoxiao Li, Zhihang Zhong, Shohei Nobuhara, Ko Nishino, Yinqiang Zheng

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 polarization-based vision applications, such as reflection removal, shape-from-polarization, 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-the-art polarization-based vision algorithms for glass segmentation and color constancy. 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 contact-free 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, both in the monochromatic and trichromatic domain, for which due attentions should be paid and counter measures be considered.

📄 PDF Abstract BibTeX arXiv:2303.17890

Code (0)

등록된 구현이 없습니다.

Tasks

Color ConstancyReflection RemovalSemantic Segmentation

Similar Papers 제목 키워드 기반

High Resolution Surface Reconstruction of Cultural Heritage Objects Using Shape from Polarization Method

2024-06-21 · F. S. Mortazavi, M. Saadatseresht

Nowadays, three-dimensional reconstruction is used in various fields like computer vision, computer graphics, mixed reality and digital twin. The three-dimensional reconstruction of cultural heritage objects is one of th…

Mixed RealitySurface Reconstruction

Polarizing Front Ends for Robust CNNs

2020-02-22 · Can Bakiskan, Soorya Gopalakrishnan, Metehan Cekic, Upamanyu Madhow 외

The vulnerability of deep neural networks to small, adversarially designed perturbations can be attributed to their "excessive linearity." In this paper, we propose a bottom-up strategy for attenuating adversarial pertur…

A Computational Analysis of Polarization on Indian and Pakistani Social Media

2020-05-20 · Aman Tyagi, Anjalie Field, Priyank Lathwal, Yulia Tsvetkov 외

Between February 14, 2019 and March 4, 2019, a terrorist attack in Pulwama, Kashmir followed by retaliatory airstrikes led to rising tensions between India and Pakistan, two nuclear-armed countries. In this work, we exam…

Embedded polarizing filters to separate diffuse and specular reflection

2018-11-06 · Laurent Valentin Jospin, Gilles Baechler, Adam Scholefield

Polarizing filters provide a powerful way to separate diffuse and specular reflection; however, traditional methods rely on several captures and require proper alignment of the filters. Recently, camera manufacturers hav…

Divide and Diverge: Polarization Incentives

2024-05-31 · Giampaolo Bonomi

We study polarization in a probabilistic voting model with aggregate shocks and a decreasing marginal utility from office rents. In equilibrium, parties offer different policies, despite being rent-motivated and ex-ante …