3260 papers • 126 benchmarks • 313 datasets
This task has no description! Would you like to contribute one?
(Image credit: Papersgraph)
These leaderboards are used to track progress in multispectral-image-super-resolution
Use these libraries to find multispectral-image-super-resolution models and implementations
No subtasks available.
This work forms the degradation process of the high-resolution multispectral (HrMS) image as a unified variational optimization problem, and alternately solve its data and prior subproblems by the designed iterative proximal gradient descent (PGD) algorithm, and unfolds the iterative algorithm into a stage-wise unfolding network, LGTEUN, for the interpretable MS pan-sharpening.
The model introduces MoE‐SM, an enhanced Mixture‐of‐Experts (MoE) to replace the Feed‐Forward inside all Transformer block, and proposes to use a combination of Normalized‐Cross‐Correlation (NCC) and Structural Similarity Index Measure (SSIM) losses, to avoid typical MSE loss limitations.
Adding a benchmark result helps the community track progress.