Mixed Causal-Acausal Assisted Compensation Model for Limited-Exposure HDR Imaging

High dynamic range (HDR) imaging has received sustained interest for its ability to capture a wider scene radiance range than conventional imaging by fusing multi-exposure images. However, increasing the number of exposures aggravates ghosting artifacts during fusion, prompting modern devices to use only one or two shots. This leads to the fact that a single exposure is unable to simultaneously preserve details in both dark and bright regions, and even dual-exposure settings are insufficient to capture the full scene radiance. Under limited exposure conditions, distinct challenges arise for both physics-driven and data-driven models, with the former struggling to model unobserved irradiance distributions and the latter having difficulty capturing diverse exposure variations, leading to unrealistic brightness artifacts in highlights and shadows. To address this problem, we propose a mixed causal–acausal assisted compensation model that integrates physics-driven and data-driven modules to generate interpolated and extrapolated pseudo-exposure images for recovering missing brightness information. The proposed model decomposes pseudo-exposure image generation into a hybrid representation consisting of a causal part reflecting radiance variation and an acausal part capturing the residual scene structure. The causal representation is derived by estimating the physics-driven intensity mapping function from adjacent exposure images while the acausal one is obtained through a data-driven attention-augmented hybrid network. Both theoretical analysis and experimental results demonstrate that the pseudo-exposure images perform well in both objective and subjective evaluations. In addition, it is validated that incorporating interpolated or extrapolated images into raw images can indeed mitigate brightness artifacts in dual-exposure fusion as well as in single-exposure enhancement.