T
Tao Lu
Researcher at Wuhan Institute of Technology
Publications - 135
Citations - 1710
Tao Lu is an academic researcher from Wuhan Institute of Technology. The author has contributed to research in topics: Face hallucination & Computer science. The author has an hindex of 14, co-authored 101 publications receiving 946 citations. Previous affiliations of Tao Lu include Wuhan University & Texas A&M University.
Papers
More filters
Journal ArticleDOI
Edge-Enhanced GAN for Remote Sensing Image Superresolution
TL;DR: A generative adversarial network (GAN)-based edge-enhancement network (EEGAN) for robust satellite image SR reconstruction along with the adversarial learning strategy that is insensitive to noise is proposed.
Journal ArticleDOI
Single Image Super-Resolution via Locally Regularized Anchored Neighborhood Regression and Nonlocal Means
TL;DR: This paper addresses the problem of learning the mapping functions between the LR and HR images based on a dictionary ofLR and HR examples by applying the local geometry prior to regularize the patch representation, and utilizing the nonlocal means filter to improve the super-resolved outcome.
Journal ArticleDOI
Multi-Memory Convolutional Neural Network for Video Super-Resolution
TL;DR: This paper proposes a multi-memory CNN (MMCNN) for video SR, cascading an optical flow network and an image-reconstruction network that shows superiority over the state-of-the-art methods in terms of PSNR and visual quality and surpasses the best counterpart method by 1 dB at most.
Proceedings ArticleDOI
Position-Patch Based Face Hallucination via Locality-Constrained Representation
TL;DR: A simpler but more effective representation scheme- Locality-constrained Representation (LcR) has been developed, which imposes a locality constraint onto the least square inversion problem to reach sparsity and locality simultaneously.
Journal ArticleDOI
A Progressive Fusion Generative Adversarial Network for Realistic and Consistent Video Super-Resolution
TL;DR: A novel progressive fusion network for video SR, in which frames are processed in a way of progressive separation and fusion for the thorough utilization of spatio-temporal information, which incorporates multi-scale structure and hybrid convolutions into the network to capture a wide range of dependencies.