High-Resolution Single-Shot Polarimetric Imaging Made Easy

TL;DR

EasyPolar introduces a multi-view imaging system with a specialized neural network to achieve high-resolution, single-shot linear polarization imaging without the resolution loss typical of existing sensors.

Contribution

The paper presents a novel triple-camera hardware setup combined with a confidence-guided neural network for accurate polarization reconstruction from multi-view data.

Findings

Achieves high-quality polarization images with a triple-camera system.

Effectively suppresses artifacts through confidence-guided multi-modal fusion.

Enhances downstream applications with improved polarization data.

Abstract

Polarization-based vision has gained increasing attention for providing richer physical cues beyond RGB images. While achieving single-shot capture is highly desirable for practical applications, existing Division-of-Focal-Plane (DoFP) sensors inherently suffer from reduced spatial resolution and artifacts due to their spatial multiplexing mechanism. To overcome these limitations without sacrificing the snapshot capability, we propose EasyPolar, a multi-view polarimetric imaging framework. Our system is grounded in the physical insight that three independent intensity measurements are sufficient to fully characterize linear polarization. Guided by this, we design a triple-camera setup consisting of three synchronized RGB cameras that capture one unpolarized view and two polarized views with distinct orientations. Building upon this hardware design, we further propose a confidence-guided polarization reconstruction network to address the potential misalignment in multi-view fusion. The network performs multi-modal feature fusion under a confidence-aware physical guidance mechanism, which effectively suppresses warping-induced artifacts and enforces explicit geometric constraints on the solution space. Experimental results demonstrate that our method achieves high-quality results and benefits various downstream tasks.