PolarVSR: A Unified Framework and Benchmark for Continuous Space-Time Polarization Video Reconstruction

2026-05-11

AI Summary

This work addresses the challenge of low frame rates and poor reconstruction quality in dynamic polarization video acquisition with mainstream Division-of-Focal-Plane (DoFP) sensors, which stems from inherent hardware limitations. To overcome this, we propose the first spatiotemporal joint framework for polarization video reconstruction. Our method introduces a polarization-aware implicit neural representation to enable continuous, high-fidelity spatial upsampling and incorporates an optical flow–guided loss to model the temporal dynamics of polarization parameters—namely, degree of linear polarization (DoLP) and angle of polarization (AoP). Key contributions include a unified spatiotemporal reconstruction architecture, the novel polarization-aware implicit representation coupled with a dynamic supervision mechanism, and the creation of the first large-scale color DoFP polarization video benchmark dataset. Experiments demonstrate that our approach significantly enhances both spatial resolution and temporal consistency.

Abstract

Polarimetric imaging captures surface polarization characteristics, such as the Degree of Linear Polarization (DoLP) and the Angle of Polarization (AoP). In mainstream Division of-Focal-Plane (DoFP) color polarization imaging, recovering polarization parameters from captured mosaic arrays remains a challenging inverse problem. Existing DoFP cameras also face hardware bottlenecks and often cannot support high-frame-rate acquisition, limiting polarimetric imaging in dynamic video tasks. These limitations motivate joint spatial and temporal enhancement. To this end, we propose the first space-time polarization video reconstruction architecture. The method jointly models polarization directions in space and time and uses a polarization-aware implicit neural representation for continuous, high-fidelity upsampling. By analyzing temporal variations in polarization parameters, we further introduce a flow-guided polarization variation loss to supervise polarization dynamics. We also establish the first large-scale color DoFP polarization video benchmark to support this research direction. Extensive experiments on this benchmark demonstrate the effectiveness of the method.

Problem

• polarimetric imaging
• DoFP
• polarization video reconstruction
• space-time enhancement
• inverse problem

Innovation

• polarization video reconstruction
• implicit neural representation
• space-time modeling
• flow-guided loss
• DoFP benchmark