Deep Polarimetric HDR Reconstruction

TL;DR

This paper introduces a deep learning-based HDR reconstruction method leveraging polarization camera data, using polarimetric cues to improve the quality of HDR images, outperforming existing algorithms.

Contribution

It presents a novel deep HDR reconstruction framework with a feature masking mechanism that utilizes polarimetric information from polarization cameras.

Findings

DPHR outperforms state-of-the-art HDR methods in qualitative evaluations.

The polarimetric cues improve feature propagation and pixel regression.

The method effectively reconstructs high-quality HDR images from polarization data.

Abstract

This paper proposes a novel learning based high-dynamic-range (HDR) reconstruction method using a polarization camera. We utilize a previous observation that polarization filters with different orientations can attenuate natural light differently, and we treat the multiple images acquired by the polarization camera as a set acquired under different exposure times, to introduce the development of solutions for the HDR reconstruction problem. We propose a deep HDR reconstruction framework with a feature masking mechanism that uses polarimetric cues available from the polarization camera, called Deep Polarimetric HDR Reconstruction (DPHR). The proposed DPHR obtains polarimetric information to propagate valid features through the network more effectively to regress the missing pixels. We demonstrate through both qualitative and quantitative evaluations that the proposed DPHR performs favorably than state-of-the-art HDR reconstruction algorithms.