文献类型：期刊文献

英文题名：MA-MFIF: When misaligned multi-focus Image fusion meets deep homography estimation

作者：Zhao, Baojun[1]; Luo, Fei[1,2]; Fuentes, Joel[3]; Ding, Weichao[1]; Gu, Chunhua[1]

机构：[1] School of Information Science and Engineering, East China University of Science and Technology, Shanghai, 200237, China; [2] Shanghai Key Laboratory of Computer Software Evaluating and Testing, Shanghai, China; [3] Department of Computer Science and Information Technologies, Universidad del Bio-Bio, Chillán, 3780000, Chile

年份：2025

卷号：84

期号：12

起止页码：10877

外文期刊名：Multimedia Tools and Applications

收录：EI(收录号：20242116114226)

语种：英文

外文关键词：Data handling - Deep learning - Image fusion

摘要：Multi-focus image fusion is a technique that combines multiple out-of-focus images to enhance the overall image quality. It has gained significant attention in recent years, thanks to the advancements in deep learning. However, one of the persistent challenges in this field is the processing of misaligned data, which can negatively impact the fusion results. To overcome this problem, a novel fusion framework with pre-registration is proposed for the fusion of misaligned multi-focus images. For pre-registration, content-aware deep homography estimation is used, which performs transfer learning on a real multi-focus image dataset to adapt to registration under defocused conditions. For fusion, a fusion module with dual-branch feature interaction is utilized to avoid invalid feature fusion and trained on real light field dataset to achieve better fusion performance. Qualitative and quantitative experimental results show that the proposed method has a 2-3 percentage point improvement in multiple evaluation metrics compared to existing advanced registration and fusion methods, and a maximum improvement of 4.83 percentage points in fusion performance when tested independently on the Lytro dataset. Additionally, We find that the value of the Qcv metric is greatly influenced by the alignment status of the input images, leading to its inability to reflect the fusion quality of aligned images. ? The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.