Variational Osmosis for Non-linear Image Fusion

TL;DR

This paper introduces a novel variational model for non-linear image fusion that leverages osmosis energy, enabling visually plausible, invariant, and minimally supervised multi-modal image fusion with superior performance.

Contribution

It presents a new non-convex variational model based on osmosis energy for non-linear image fusion, with a primal-dual algorithm for practical implementation.

Findings

Outperforms state-of-the-art methods in image fusion tasks.

Requires minimal supervision and parameter tuning.

Effective in applications like face fusion, color transfer, and heritage conservation.

Abstract

We propose a new variational model for non-linear image fusion. Our approach is based on the use of an osmosis energy term related to the one studied in Vogel et al. (2013) and Weickert et al. (2013) The minimization of the proposed non-convex energy realizes visually plausible image data fusion, invariant to multiplicative brightness changes. On the practical side, it requires minimal supervision and parameter tuning and can encode prior information on the structure of the images to be fused. For the numerical solution of the proposed model, we develop a primal-dual algorithm and we apply the resulting minimization scheme to solve multi-modal face fusion, color transfer and cultural heritage conservation problems. Visual and quantitative comparisons to state-of-the-art approaches prove the out-performance and the flexibility of our method.