J
Junhui Hou
Researcher at City University of Hong Kong
Publications - 236
Citations - 6392
Junhui Hou is an academic researcher from City University of Hong Kong. The author has contributed to research in topics: Computer science & Point cloud. The author has an hindex of 27, co-authored 192 publications receiving 2712 citations. Previous affiliations of Junhui Hou include Northwestern Polytechnical University & Southeast University.
Papers
More filters
Posted Content
Deep Attention-guided Graph Clustering with Dual Self-supervision.
TL;DR: Wang et al. as discussed by the authors proposed a deep attention-guided graph clustering with dual self-supervision (DAGC) method, which first utilizes a heterogeneity-wise fusion module to adaptively integrate the features of an auto-encoder and a graph convolutional network in each layer and then uses a scale-wise fused module to dynamically concatenate the multi-scale features in different layers.
Journal ArticleDOI
Rank-Enhanced Low-Dimensional Convolution Set for Hyperspectral Image Denoising
Zhiyu Zhu,Hui Liu,Junhui Hou +2 more
TL;DR: This paper proposes rank-enhanced low-dimensional convolution set (Re-ConvSet), which separately performs 1-D convolution along the three dimensions of an HS image side-by-side, and then aggregates the resulting spatial-spectral embeddings via a learnable compression layer.
Journal ArticleDOI
Differentiable Deformation Graph-Based Neural Non-rigid Registration
Posted Content
Deep Magnification-Flexible Upsampling over 3D Point Clouds
TL;DR: In this paper, an end-to-end learning-based framework is proposed to generate dense point clouds from given sparse point clouds to model the underlying geometric structures of objects/scenes.
Posted Content
Learning High-fidelity Light Field Images From Hybrid Inputs.
TL;DR: This paper proposes a novel end-to-end learning-based approach for reconstructing a high-fidelity LF image with a hybrid input that not only improves the PSNR more than 2 dB, but also preserves the LF structure much better.