PolarVSR: A Unified Framework and Benchmark for Continuous Space-Time Polarization Video Reconstruction
This work addresses the bottleneck of low-frame-rate and low-resolution polarization video acquisition for dynamic polarimetric imaging tasks, providing a unified framework and benchmark.
This paper introduces the first space-time polarization video reconstruction framework, PolarVSR, which jointly models polarization directions in space and time using a polarization-aware implicit neural representation for continuous upsampling. It also establishes the first large-scale color DoFP polarization video benchmark, demonstrating effectiveness through extensive experiments.
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.