HDR reconstruction from a single exposure LDR using texture and structure dual-stream generation

Reconstructing high dynamic range (HDR) imagery from a single low dynamic range (LDR) photograph presents substantial challenges. The challenges are primarily due to the loss of details and information in regions of underexposure or overexposure due to quantization and saturation inherent to camera sensors. Traditional learning-based approaches often struggle with distinguishing overexposed regions within an object from the background, leading to compromised detail retention in these critical areas. Our methodology focuses on meticulously reconstructing structural and textural details to preserve the integrity of the structural information. We propose a new two-stage model architecture for HDR image reconstruction, including a dual-stream network and a feature fusion stage. The dual-stream network is designed to reconstruct structural and textural details, while the feature fusion stage aims to minimize artifacts by utilizing the reconstructed information. We have demonstrated that our proposed method performs better than other state-of-the-art single-image HDR reconstruction algorithms in various quality metrics.