Confidence driven TGV fusion
This work addresses data fusion challenges in computer vision, particularly for depth imaging, but it appears incremental as it builds on existing variational methods with confidence-driven enhancements.
The authors tackled the problem of spatially varying variational data fusion by introducing a model that jointly estimates data and confidence values based on spatial coherence, and they evaluated it on depth image fusion using synthetic and real datasets, achieving performance improvements as demonstrated in their experiments.
We introduce a novel model for spatially varying variational data fusion, driven by point-wise confidence values. The proposed model allows for the joint estimation of the data and the confidence values based on the spatial coherence of the data. We discuss the main properties of the introduced model as well as suitable algorithms for estimating the solution of the corresponding biconvex minimization problem and their convergence. The performance of the proposed model is evaluated considering the problem of depth image fusion by using both synthetic and real data from publicly available datasets.