Robust HDR Video Synthesis Using Superpixel-Based Illumination Invariant Motion Estimation

We propose a novel high dynamic range (HDR) video synthesis algorithm from alternatively exposed low dynamic range (LDR) videos. We first develop a superpixel-based motion estimation technique using an illumination-invariant feature descriptor. Then, we merge the warped frames to obtain the HDR frame. Experimental results demonstrate that the proposed algorithm provides high-quality HDR videos compared to state-of-the-art algorithms.