High-Resolution Single-Shot Polarimetric Imaging Made Easy

2026-04-07

AI Summary

Division-of-Focal-Plane (DoFP) polarimetric imaging suffers from reduced spatial resolution and artifact generation due to its single-shot acquisition scheme. To address these limitations, this work proposes EasyPolar, a multi-view polarimetric imaging framework that integrates, for the first time, a three-camera synchronized capture system—comprising one unpolarized and two orthogonally polarized views—with a physics-guided confidence-based fusion mechanism. By leveraging multimodal feature fusion, a confidence-guided reconstruction network, and geometric constraint optimization, the proposed method preserves the advantage of single-shot acquisition while effectively overcoming the inherent resolution and artifact constraints of DoFP sensors. This approach significantly enhances polarization image quality and improves performance in downstream vision tasks.

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.

Problem

• polarimetric imaging
• single-shot
• spatial resolution
• artifacts
• Division-of-Focal-Plane

Innovation

• single-shot polarimetric imaging
• multi-view fusion
• confidence-guided reconstruction
• high-resolution polarization
• physical guidance