Benchmarking and comparing multi-exposure image fusion algorithms

Multi-exposure image fusion (MEF) is an important area in computer vision and has attracted increasing interests recent years. Apart from conventional algorithms, deep learning techniques have also been applied to MEF. However, although many efforts made on developing MEF the lack of benchmarking studies makes it difficult perform fair comprehensive performance comparison among thus hindering development this field significantly. In paper, we fill gap by proposing a benchmark multi-exposure (MEFB), which consists test set 100 pairs, code library 21 20 evaluation metrics, 2100 fused images, software toolkit. To best our knowledge, first study This paper gives literature review methods with focus learning-based algorithms. Extensive experiments conducted using MEFB for identifying effective We expect that will serve as platform researchers compare