L
Longguang Wang
Researcher at National University of Defense Technology
Publications - 66
Citations - 1613
Longguang Wang is an academic researcher from National University of Defense Technology. The author has contributed to research in topics: Computer science & Motion compensation. The author has an hindex of 13, co-authored 43 publications receiving 408 citations.
Papers
More filters
Proceedings ArticleDOI
Learning Parallax Attention for Stereo Image Super-Resolution
TL;DR: A parallax-attention mechanism with a global receptive field along the epipolar line to handle different stereo images with large disparity variations is introduced and a new and the largest dataset for stereo image SR is proposed.
Proceedings ArticleDOI
Unsupervised Degradation Representation Learning for Blind Super-Resolution
TL;DR: Wang et al. as discussed by the authors proposed an unsupervised degradation representation learning scheme for blind super-resolution without explicit degradation estimation, which can extract discriminative representations to obtain accurate degradation information.
Proceedings ArticleDOI
Exploring Sparsity in Image Super-Resolution for Efficient Inference
TL;DR: Wang et al. as mentioned in this paper explored the sparsity in image SR to improve inference efficiency of SR networks and developed a Sparse Mask SR (SMSR) network to learn sparse masks to prune redundant computation.
Journal ArticleDOI
Deep Video Super-Resolution Using HR Optical Flow Estimation
TL;DR: Wang et al. as mentioned in this paper proposed an end-to-end video super-resolution network to super-resolve both optical flows and images, which can exploit temporal dependency between consecutive frames.
Journal ArticleDOI
Deformable 3D Convolution for Video Super-Resolution
TL;DR: A deformable 3D convolution network (D3Dnet) is proposed to incorporate spatio-temporal information from both spatial and temporal dimensions for video SR, and achieves state-of-the-art SR performance.