Image matching in Bayer RAW domain to remove ghosting in multi-exposure image fusion

Multi exposure image fusion is a well-known approach adopted to create High Dynamic Range (HDR) images and emulate the Human Visual System (HVS) using Standard Dynamic Range (SDR) cameras. The main limitation of current multi-exposure image fusion techniques is their inability to compensate for moving objects in a scene and camera shake. Previous attempts to solve camera shake have been able to accurately align the multi-exposure images that have static backgrounds prior to their fusion. Nonetheless, image alignment cannot solve the issue of ghosting artefacts due to moving objects. In this paper, a local motion compensation technique is proposed to efficiently remove ghosting artefacts due to both, camera shake and object movement in the scene. We provide subjective experimental results to demonstrate the ability of proposed method to remove ghosting artefacts in HDR images.