146 citations · 170 across the 3 of their papers we have counts for
6 papers
From General to Specific: Online Updating for Blind Super-Resolution
Shang Li, Guixuan Zhang, Zhengxiong Luo +3
Most deep learning-based super-resolution (SR) methods are not image-specific: 1) They are trained on samples synthesized by predefined degradations (e.g. bicubic downsampling), re…
End-to-end Alternating Optimization for Blind Super Resolution
Zhengxiong Luo, Yan Huang, Shang Li +2
Previous methods decompose the blind super-resolution (SR) problem into two sequential steps: \textit{i}) estimating the blur kernel from given low-resolution (LR) image and \texti…
Efficient Human Pose Estimation by Learning Deeply Aggregated Representations
Zhengxiong Luo, Zhicheng Wang, Yuanhao Cai +6
In this paper, we propose an efficient human pose estimation network (DANet) by learning deeply aggregated representations. Most existing models explore multi-scale information mai…
Rethinking the Heatmap Regression for Bottom-up Human Pose Estimation
Zhengxiong Luo, Zhicheng Wang, Yan Huang +2
Heatmap regression has become the most prevalent choice for nowadays human pose estimation methods. The ground-truth heatmaps are usually constructed via covering all skeletal keyp…
Unfolding the Alternating Optimization for Blind Super Resolution
Zhengxiong Luo, Yan Huang, Shang Li +2
Previous methods decompose blind super resolution (SR) problem into two sequential steps: \textit{i}) estimating blur kernel from given low-resolution (LR) image and \textit{ii}) r…
Learning Delicate Local Representations for Multi-Person Pose Estimation
Yuanhao Cai, Zhicheng Wang, Zhengxiong Luo +7
In this paper, we propose a novel method called Residual Steps Network (RSN). RSN aggregates features with the same spatial size (Intra-level features) efficiently to obtain delica…