Geoinformatics Unit

Wei HE


Current Position

Wei He is currently a postdoctoral researcher at Geoinformatics Unit, the RIKEN Center for Advanced Intelligence Project (AIP), Japan. His research interests include remote sensing image restoration, low-rank modeling, and deep learning.
He is a member of the IEEE and IEEE Geoscience and Remote Sensing Society (GRSS).


2018 Jan - Present    Postdoctoral Researcher, RIKEN AIP, Japan
2012 Sep - 2017 Jun    Ph.D. LIESMARS, Wuhan University, Wuhan, China

Journal Papers

  1. W. He, N. Yokoya, L. Yuan, and Q. Zhao, " Remote sensing image reconstruction using tensor ring completion and total-variation ," IEEE Trans. Geosci. Remote Sens. (accepted for publication), 2019.
    Quick Abstract

    Abstract: Time-series remote sensing (RS) images are often corrupted by various types of missing information such as dead pixels, clouds, and cloud shadows that significantly influence the subsequent applications. In this paper, we introduce a new low-rank tensor decomposition model, termed tensor ring (TR) decomposition, to the analysis of RS datasets and propose a TR completion method for the missing information reconstruction. The proposed TR completion model has the ability to utilize the low-rank property of time-series RS images from different dimensions. To furtherly explore the smoothness of the RS image spatial information, total-variation regularization is also incorporated into the TR completion model. The proposed model is efficiently solved using two algorithms, the augmented Lagrange multiplier (ALM) and the alternating least square (ALS) methods. The simulated and real data experiments show superior performance compared to other state-of-the-art low-rank related algorithms.

  2. W. He and N. Yokoya, " Multi-temporal Sentinel-1 and -2 data fusion for optical image simulation ," ISPRS International Journal of Geo-Information, vol. 7, no. 10, pp. 389, 2018.
    PDF    Quick Abstract

    Abstract: In this paper, we present the optical image simulation from synthetic aperture radar (SAR) data using deep learning based methods. Two models, i.e., optical image simulation directly from the SAR data and from multi-temporal SAR-optical data, are proposed to testify the possibilities. The deep learning based methods that we chose to achieve the models are a convolutional neural network (CNN) with a residual architecture and a conditional generative adversarial network (cGAN). We validate our models using the Sentinel-1 and -2 datasets. The experiments demonstrate that the model with multi-temporal SAR-optical data can successfully simulate the optical image, meanwhile, the model with simple SAR data as input failed. The optical image simulation results indicate the possibility of SAR-optical information blending for the subsequent applications such as large-scale cloud removal, and optical data temporal super-resolution. We also investigate the sensitivity of the proposed models against the training samples, and reveal possible future directions.

Conference Papers

  1. W. He, Q. Yao, C. Li, N. Yokoya, and Q. Zhao, "Non-local meets global: An integrated paradigm for hyperspectral denoising," Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
  2. C. Li, W. He, L. Yuan, Z. Sun, and Q. Zhao, "Guaranteed matrix completion under multiple linear transformations," Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
  3. W. He, L. Yuan, and N. Yokoya, "Total-variation-regularized tensor ring completion for remote sensing image reconstruction," International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019.
  4. H. Xu, H. Zhang, W. He, and L. Zhang, "Superpixel based dimension reduction for hyperspectral imagery," IEEE International Geoscience and Remote Sensing Symposium, 2018.