Abstract
We propose a robust high dynamic range (HDR) video synthesis algorithm using the superpixel-based illuminance-invariant motion estimation technique. The proposed algorithm first selects an input frame in an alternating exposed input video as the reference. Then, the correspondences between two adjacent frames are estimated by employing a feature descriptor, which is robust against illuminance variation, and a superpixel segmentation technique. Next, the input frames are warped to the reference frame using the estimated motion maps. Finally, the final HDR frame is synthesized by constructing a weight map, which can handle complex motions and poor exposures by considering the underlying structures in the input frames. Experimental results on real test sequences show that the proposed algorithm can provide high-quality HDR videos compared with those obtained by state-of-the-art algorithms in terms of both subjective and objective evaluations.
Highlights
High dynamic range (HDR) imaging is a technique used in photography to capture a greater dynamic range of luminosity than is possible with standard digital imaging or photographic devices [1], [2]
In this work, based on the observation that the quality of a synthesized HDR video relies on accuracy of the motion estimation technique, we propose a robust HDR video synthesis algorithm from an alternatively exposed low dynamic range (LDR) video using superpixel-based illuminance-invariant motion estimation
We provide more algorithmic details of the superpixel-based motion estimation and develop a new weighting function for HDR video synthesis
Summary
High dynamic range (HDR) imaging is a technique used in photography to capture a greater dynamic range of luminosity than is possible with standard digital imaging or photographic devices [1], [2]. HDR VIDEO SYNTHESIS Because the hardware-based HDR imaging systems [6]–[10] need not handle motion information, they may be directly used to capture HDR videos These approaches require specific optical components and often fail to provide high-quality results in regions with high contrast. Kalantari et al [19] first adjusted the brightness of a frame with the reference frame to compensate for the exposure differences using the CRF [3] They employed optical flow-based registration to enhance the temporal coherency using the patch-based technique to address the non-rigid motion and to correct the correspondences. They used the rank minimization technique and multi-scale regression to respectively obtain the background and foreground of the scene This algorithm is considered to be the state-of-the-art for motion-estimation-based HDR video synthesis. Because the input frames are captured under different exposure conditions, conventional motion estimation techniques cannot be applied directly to determine the correspondences
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
