MFFW: A new dataset for multi-focus image fusion

TL;DR

This paper introduces MFFW, a new real-world dataset for multi-focus image fusion that highlights the defocus spread effect, challenging existing methods and providing a new benchmark for robustness in complex scenes.

Contribution

The paper presents MFFW, a novel dataset with real-world images exhibiting defocus spread effect, enabling better evaluation of multi-focus image fusion methods under realistic conditions.

Findings

Most state-of-the-art methods perform poorly on MFFW.

MFFW contains more complex scenes than previous datasets.

Defocus spread effect significantly impacts fusion quality.

Abstract

Multi-focus image fusion (MFF) is a fundamental task in the field of computational photography. Current methods have achieved significant performance improvement. It is found that current methods are evaluated on simulated image sets or Lytro dataset. Recently, a growing number of researchers pay attention to defocus spread effect, a phenomenon of real-world multi-focus images. Nonetheless, defocus spread effect is not obvious in simulated or Lytro datasets, where popular methods perform very similar. To compare their performance on images with defocus spread effect, this paper constructs a new dataset called MFF in the wild (MFFW). It contains 19 pairs of multi-focus images collected on the Internet. We register all pairs of source images, and provide focus maps and reference images for part of pairs. Compared with Lytro dataset, images in MFFW significantly suffer from defocus spread effect. In addition, the scenes of MFFW are more complex. The experiments demonstrate that most state-of-the-art methods on MFFW dataset cannot robustly generate satisfactory fusion images. MFFW can be a new baseline dataset to test whether an MMF algorithm is able to deal with defocus spread effect.