Halder: Hierarchical Attention-Guided Learning with Detail-Refinement for Multi-Exposure Image Fusion

Deep learning techniques have yielded impressive progress in the field of computational imaging. Existing approaches ignore designing specific constrain on illumination or edges, making them limited in handling asymmetric halos and more likely to generate a fusion result with color discrepancy or blurred edges. To alleviate these issues, we propose a hierarchical attention-guided learning with detail-refinement, termed as HALDeR, to tackle the multi-exposure fusion (MEF) task in a coarse-to-fine manner. Firstly, a hierarchical attention network is designed to produce a fusion result by calculating well-exposed areas under different illumination. Secondly, we develop a collaborative-refine module for preventing the missing details and correcting distorted color simultaneously. Moreover, adversarial learning is employed at end of our network, which can effectively alleviate other remaining artifacts (e.g., ringing effect and noises). Extensive quantitative and qualitative results on two publicly available datasets demonstrate that our HALDeR performs favorably against the state-of-the-art methods in generating vivid color and faithful detail. Source code will be available at https://github.com/JinyuanLiu-CV/HALDeR.