Beyond Visual Attractiveness: Physically Plausible Single Image HDR Reconstruction for Spherical Panoramas
This work addresses the need for physically plausible HDR reconstruction in computer vision, particularly for industrial applications, but it is incremental as it builds on existing single-shot methods by adding regularization.
The paper tackles the problem of single-shot HDR reconstruction for spherical panoramas by introducing physical illuminance constraints, resulting in HDR images that maintain high visual quality and achieve top illuminance prediction accuracy compared to baseline methods.
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.