Variational pansharpening by exploiting cartoon-texture similarities

X Tian, Y Chen, C Yang, J Ma - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
… This enables that the fused high-spatial resolution MS image … texture components from PAN
and MS images. To explore such … -sampled fused MS image is consistent with the MS image, …

A variational pansharpening method based on gradient sparse representation

…, Y Chen, C Yang, X Gao, J Ma - IEEE Signal Processing …, 2020 - ieeexplore.ieee.org
… As a result, the spatial quality of the fused MS image can be improved. … fused MS and
LR MS images. By further incorporating a constraint from the estimated HR MS gradients, we …

Image fusion meets deep learning: A survey and perspective

H Zhang, H Xu, X Tian, J Jiang, J Ma - Information Fusion, 2021 - Elsevier
… operations on the original MS and PAN images to obtain the … MS image is regarded as the
reference image. In contrast, the unsupervised methods are directly trained on the original MS

MS2DG-Net: Progressive correspondence learning via multiple sparse semantics dynamic graph

L Dai, Y Liu, J Ma, L Wei, T Lai… - Proceedings of the …, 2022 - openaccess.thecvf.com
MS^ 2 DG-Net dynamically builds sparse semantics graphs based on sparse semantics …
Extensive experiments prove that MS^ 2 DG-Net outperforms state-of-the-art methods in outlier …

A review of multimodal image matching: Methods and applications

X Jiang, J Ma, G Xiao, Z Shao, X Guo - Information Fusion, 2021 - Elsevier
Multimodal image matching, which refers to identifying and then corresponding the same or
similar structure/content from two or more images that are of significant modalities or …

VP-Net: An interpretable deep network for variational pansharpening

X Tian, K Li, Z Wang, J Ma - IEEE Transactions on Geoscience …, 2021 - ieeexplore.ieee.org
… Considering the spectral difference of various satellite multispectral (MS) imaging platforms,
… a data fidelity term from the low-resolution MS image. Specifically, we build the VP-Net by …

Deep learning-based face super-resolution: A survey

J Jiang, C Wang, X Liu, J Ma - ACM Computing Surveys (CSUR), 2021 - dl.acm.org
… -SSIM) [43] is proposed, which divides the image into multiple windows, first assesses
SSIM for every window separately, and then converges them to obtain MS-SSIM. …

Variation-Net: Interpretable variation-inspired deep network for pansharpening

K Li, W Zhang, X Tian, J Ma, H Zhou… - 2021 IEEE International …, 2021 - ieeexplore.ieee.org
… (PAN) and multispectral (MS) images for a highresolution MS image. We first … MS images
in the real situation is complex and nonlinear, we explore the similarity between PAN and MS

Progressive fusion video super-resolution network via exploiting non-local spatio-temporal correlations

…, Z Wang, K Jiang, J Jiang, J Ma - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
… 3DFS needs about 1331 ms. Our model PFS takes about 409 ms to reconstruct one frame …
[38] Zhongyuan Wang, Peng Yi, Kui Jiang, Junjun Jiang, Zhen Han, Tao Lu, and Jiayi Ma. Multi…

FusionNDVI: A computational fusion approach for high-resolution normalized difference vegetation index

X Tian, M Zhang, C Yang, J Ma - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
… Especially, we first adopt a large amount of test data, including 165 MS/PAN images from
the Gaofen-1 data set and 142 MS/PAN images from the Gaofen-2 data set, to verify the …