Search papers, labs, and topics across Lattice.
This paper introduces EasyPolar, a multi-view polarimetric imaging framework using three synchronized RGB cameras (one unpolarized, two polarized) to achieve single-shot, high-resolution polarization imaging. They leverage the principle that three independent intensity measurements can fully characterize linear polarization, enabling reconstruction without the resolution loss inherent in Division-of-Focal-Plane sensors. A confidence-guided polarization reconstruction network fuses multi-modal features, mitigating misalignment artifacts and enforcing geometric constraints, leading to high-quality polarization information.
Unlock high-resolution polarization imaging with a surprisingly simple three-camera setup and a confidence-guided reconstruction network, bypassing the limitations of traditional DoFP sensors.
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.
