Simultaneous High Dynamic Range and Superresolution Imaging without Regularization

Abstract

Modern digital camera sensors capture only a limited amplitude and frequency range of the irradiance of a scene. A recent trend is to acquire and combine multiple images to raise the quality of the final image. Multi-image techniques are used in high dynamic range processing, where multiple exposure times are used to reconstruct the full range of irradiance. With multi-image superresolution, the difference between sampling grids caused by the motion of the camera is used to generate a high resolution image. It is possible to combine these two processes into one to generate a superresolved image with a full dynamic range. In this paper, we study the reconstruction error of high dynamic range superresolution imaging without regularization, under an affine motion hypothesis. From this study, we deduce a strategy for choosing the number of images and the exposure times, which makes the unregularized problem well conditioned. With these acquisition parameters, if the affine motion hypothesis holds and sufficiently long exposure time is available, the recovery of all the amplitude and frequency content of the scene irradiance is guaranteed.