Unsupervised Learning Based Multi-Scale Exposure Fusion

TL;DR

This paper introduces an unsupervised learning method for multi-scale exposure fusion that employs novel loss functions and attention mechanisms to produce higher quality HDR images from differently exposed LDR images.

Contribution

It proposes new loss functions utilizing all images in the scene and integrates a multi-scale attention module, advancing the quality and versatility of exposure fusion.

Findings

Outperforms state-of-the-art exposure fusion algorithms

Effectively preserves scene depth and local contrast

Enables exposure interpolation and extrapolation

Abstract

Unsupervised learning based multi-scale exposure fusion (ULMEF) is efficient for fusing differently exposed low dynamic range (LDR) images into a higher quality LDR image for a high dynamic range (HDR) scene. Unlike supervised learning, loss functions play a crucial role in the ULMEF. In this paper, novel loss functions are proposed for the ULMEF and they are defined by using all the images to be fused and other differently exposed images from the same HDR scene. The proposed loss functions can guide the proposed ULMEF to learn more reliable information from the HDR scene than existing loss functions which are defined by only using the set of images to be fused. As such, the quality of the fused image is significantly improved. The proposed ULMEF also adopts a multi-scale strategy that includes a multi-scale attention module to effectively preserve the scene depth and local contrast in the fused image. Meanwhile, the proposed ULMEF can be adopted to achieve exposure interpolation and exposure extrapolation. Extensive experiments show that the proposed ULMEF algorithm outperforms state-of-the-art exposure fusion algorithms.