Beyond Visual Attractiveness: Physically Plausible Single Image HDR Reconstruction for Spherical Panoramas

TL;DR

This paper presents a novel single-image HDR reconstruction method for spherical panoramas that incorporates physical illuminance constraints, resulting in visually appealing and physically plausible HDR images with improved illuminance accuracy.

Contribution

It introduces physical illuminance constraints into single-shot HDR reconstruction, enhancing physical plausibility without sacrificing visual quality.

Findings

HDR images with physical constraints outperform baselines in illuminance accuracy

Method produces visually appealing HDRs that are physically plausible

Large dataset used for comprehensive evaluation

Abstract

HDR reconstruction is an important task in computer vision with many industrial needs. The traditional approaches merge multiple exposure shots to generate HDRs that correspond to the physical quantity of illuminance of the scene. However, the tedious capturing process makes such multi-shot approaches inconvenient in practice. In contrast, recent single-shot methods predict a visually appealing HDR from a single LDR image through deep learning. But it is not clear whether the previously mentioned physical properties would still hold, without training the network to explicitly model them. In this paper, we introduce the physical illuminance constraints to our single-shot HDR reconstruction framework, with a focus on spherical panoramas. By the proposed physical regularization, our method can generate HDRs which are not only visually appealing but also physically plausible. For evaluation, we collect a large dataset of LDR and HDR images with ground truth illuminance measures. Extensive experiments show that our HDR images not only maintain high visual quality but also top all baseline methods in illuminance prediction accuracy.