Neural Augmented Exposure Interpolation for HDR Imaging

Zhengguo Li, Chaobing Zheng, Jinghong Zheng, Shiqian Wu

Abstract: Brightness order reversal usually appears when two large-exposure-ratio images of a high dynamic range scene are directly fused together by an existing multi-scale exposure fusion algorithm. To address the problem, a novel neural augmented framework is introduced to interpolate an image with the medium exposure by integrating physics-driven and data-driven approaches. The physics-driven method infers high-frequency information while the data-driven approach learns remaining information for the interpolated image. The interpolated image and two large-exposure-ratio images are fused together. Experimental results show that the proposed framework can indeed solve the brightness order reversal problem for the fusion of of two large-exposure-ratio images.