DRHDR: A Dual branch Residual Network for Multi-Bracket High Dynamic Range Imaging
This work addresses ghosting artifacts in HDR imaging for photography applications, presenting an incremental improvement in method efficiency.
The paper tackled the problem of fusing multiple brackets from dynamic scenes for high dynamic range imaging by proposing DRHDR, a dual branch residual network, achieving high-quality results with constrained computational resources.
We introduce DRHDR, a Dual branch Residual Convolutional Neural Network for Multi-Bracket HDR Imaging. To address the challenges of fusing multiple brackets from dynamic scenes, we propose an efficient dual branch network that operates on two different resolutions. The full resolution branch uses a Deformable Convolutional Block to align features and retain high-frequency details. A low resolution branch with a Spatial Attention Block aims to attend wanted areas from the non-reference brackets, and suppress displaced features that could incur on ghosting artifacts. By using a dual branch approach we are able to achieve high quality results while constraining the computational resources required to estimate the HDR results.