Answers are grounded in this paper and cite their sources.
Multi-exposure image fusion (MEF) combines differently exposed images of the same high-dynamic-range scene to produce a high-quality low-dynamic-range image. However, existing MEF methods often struggle to preserve fine details in extremely bright and dark regions and may introduce halo artifacts and edge distortions around high-contrast boundaries. To address these challenges, we propose a chromatic-aware MEF framework with dynamic parameter selection and two-scale decomposition. Specifically, we incorporate RGB chromatic gradient information into edge-aware weight refinement to enhance cross-channel structural consistency and suppress halo artifacts. A global structure-adaptive parameter selection strategy based on percentile-based gradient aggregation dynamically determines the filtering radius and regularization parameter, thereby eliminating the need for manual parameter tuning. In addition, a two-scale coarse–residual decomposition separately preserves global luminance balance and fine-scale textural details. Extensive comparisons with eight state-of-the-art methods demonstrate superior perceptual quality, while quantitative evaluations confirm the effectiveness of the proposed framework. The framework maintains low computational overhead, with an average processing time of 0.77 s per image on a standard CPU, making it suitable for resource-constrained imaging applications.
No takes yet. Share an insight, caveat, or question.
Rahul Dinesh Kumar (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: