T
Tianyu Wang
Researcher at The Chinese University of Hong Kong
Publications - 15
Citations - 708
Tianyu Wang is an academic researcher from The Chinese University of Hong Kong. The author has contributed to research in topics: Computer science & Shadow. The author has an hindex of 5, co-authored 11 publications receiving 315 citations. Previous affiliations of Tianyu Wang include City University of Hong Kong.
Papers
More filters
Proceedings ArticleDOI
Spatial Attentive Single-Image Deraining With a High Quality Real Rain Dataset
TL;DR: A semi-automatic method that incorporates temporal priors and human supervision to generate a high-quality clean image from each input sequence of real rain images is proposed, and a novel SPatial Attentive Network (SPANet) is proposed to remove rain streaks in a local-to-global manner.
Posted Content
Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset.
TL;DR: Wang et al. as mentioned in this paper proposed a semi-automatic method that incorporates temporal priors and human supervision to generate a high-quality clean image from each input sequence of real rain images.
Journal ArticleDOI
SAC-Net: Spatial Attenuation Context for Salient Object Detection
TL;DR: A new deep neural network design for salient object detection by maximizing the integration of local and global image context within, around, and beyond the salient objects by embedding the spatial attenuation context module to recurrently translate and aggregate the context features.
Proceedings ArticleDOI
Instance Shadow Detection
TL;DR: Wang et al. as mentioned in this paper proposed a light-guided instance shadow-object association (LISA) framework to automatically predict the shadow and object instances, together with the shadow object associations and light direction.
Journal ArticleDOI
Single-Image Real-Time Rain Removal Based on Depth-Guided Non-Local Features
TL;DR: Wang et al. as discussed by the authors analyzed the visual effects of rain subject to scene depth and formulated a rain imaging model that collectively considered rain streaks and fog, and designed a novel real-time end-to-end deep neural network, for which they trained to learn the depth-guided non-local features and to regress a residual map to produce a rain-free output image.