Variational Osmosis for Non-linear Image Fusion
This addresses image fusion problems for applications like cultural heritage conservation, but appears incremental as it builds on prior osmosis energy work.
The authors tackled the problem of non-linear image fusion by proposing a variational model with an osmosis energy term, achieving visually plausible fusion invariant to multiplicative brightness changes with minimal supervision and parameter tuning. Their method outperformed state-of-the-art approaches in visual and quantitative comparisons on tasks like multi-modal face fusion, color transfer, and cultural heritage conservation.
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.