An adaptive method to recover high dynamic range images from multi-camera systems in back-lighting scenario

Abstract The reconstruction of multi-view high dynamic range images faces several challenges, including holes and artifact in the disparity map in non-linear and large baseline between the involved cameras. Furthermore, these challenges increased when a back-lighting scenario is involved, with the currently industrial growth. To dispense the disparity map estimation and it’s related challenges, and generate backlighting multi-view high dynamic range images, we propose a method that relays on accurately detected and matched features between the adjustment viewpoints instead of the estimation of the disparity map, thus providing a flexibility on the camera baseline. Next, we estimate exposure gain between the matched features. After that, we restore the multi-view low dynamic range images based on the estimated gain, and generate a final high dynamic range image per view. Experimental results demonstrate superior performance for the proposed method over state-of-the-art methods in both objective and subject comparisons. These results suggest that our method is suitable to improve the visual quality of multi-view low dynamic range images captured in low back-lighting conditions via commercial cameras sparsely located among each other in any general public infrastructure.