Real-MFF: A Large Realistic Multi-focus Image Dataset with Ground Truth
This provides a benchmark for evaluating and training algorithms in multi-focus image fusion, which is incremental as it addresses a data gap rather than proposing a new method.
The authors tackled the lack of a large and realistic dataset for multi-focus image fusion by introducing Real-MFF, a dataset with 710 pairs of source images and ground truth images, and used it to evaluate 10 typical algorithms.
Multi-focus image fusion, a technique to generate an all-in-focus image from two or more partially-focused source images, can benefit many computer vision tasks. However, currently there is no large and realistic dataset to perform convincing evaluation and comparison of algorithms in multi-focus image fusion. Moreover, it is difficult to train a deep neural network for multi-focus image fusion without a suitable dataset. In this letter, we introduce a large and realistic multi-focus dataset called Real-MFF, which contains 710 pairs of source images with corresponding ground truth images. The dataset is generated by light field images, and both the source images and the ground truth images are realistic. To serve as both a well-established benchmark for existing multi-focus image fusion algorithms and an appropriate training dataset for future development of deep-learning-based methods, the dataset contains a variety of scenes, including buildings, plants, humans, shopping malls, squares and so on. We also evaluate 10 typical multi-focus algorithms on this dataset for the purpose of illustration.