Hierarchical Back Projection Network for Image Super-Resolution
Zhi-Song Liu,Li-Wen Wang,Chu-Tak Li,Wan-Chi Siu +3 more
- pp 2041-2050
TLDR
The Hierarchical Back Projection Network (HBPN) as mentioned in this paper cascades multiple HourGlass (HG) modules to bottom-up and top-down process features across all scales to capture various spatial correlations and then consolidates the best representation for reconstruction.Abstract:
Deep learning based single image super-resolution methods use a large number of training datasets and have recently achieved great quality progress both quantitatively and qualitatively. Most deep networks focus on nonlinear mapping from low-resolution inputs to high-resolution outputs via residual learning without exploring the feature abstraction and analysis. We propose a Hierarchical Back Projection Network (HBPN), that cascades multiple HourGlass (HG) modules to bottom-up and top-down process features across all scales to capture various spatial correlations and then consolidates the best representation for reconstruction. We adopt the back projection blocks in our proposed network to provide the error correlated up-and down-sampling process to replace simple deconvolution and pooling process for better estimation. A new Softmax based Weighted Reconstruction (WR) process is used to combine the outputs of HG modules to further improve super-resolution. Experimental results on various datasets (including the validation dataset, NTIRE2019, of the Real Image Super-resolution Challenge) show that our proposed approach can achieve and improve the performance of the state-of-the-art methods for different scaling factors.read more
Citations
More filters
Journal ArticleDOI
Lightening Network for Low-Light Image Enhancement
TL;DR: A novel Deep Lightening Network (DLN) that benefits from the recent development of Convolutional Neural Networks (CNNs) is proposed that outperforms other methods under both objective and subjective metrics.
Proceedings ArticleDOI
NTIRE 2019 Challenge on Real Image Super-Resolution: Methods and Results
Jianrui Cai,Shuhang Gu,Radu Timofte,Lei Zhang,Xiao Liu,Ding Yukang,Dongliang He,Chao Li,Yi Fu,Shilei Wen,Ruicheng Feng,Jinjin Gu,Yu Qiao,Chao Dong,Dongwon Park,Se Young Chun,Sanghoon Yoon,Junhyung Kwak,Donghee Son,Syed Waqas Zamir,Aditya Arora,Salman H. Khan,Fahad Shahbaz Khan,Ling Shao,Zhengping Wei,Lei Liu,Hong Cai,Darui Li,Fujie Gao,Zheng Hui,Xiumei Wang,Xinbo Gao,Guoan Cheng,Ai Matsune,Qiuyu Li,Leilei Zhu,Huaijuan Zang,Shu Zhan,Yajun Qiu,Ruxin wang,Jiawei Li,Yongcheng Jing,Mingli Song,Pengju Liu,Kai Zhang,Jingdong Liu,Jiye Liu,Hongzhi Zhang,Wangmeng Zuo,Wenyi Tang,Jing Liu,Youngjung Kim,Changyeop Shin,Minbeom Kim,Sungho Kim,Pablo Navarrete Michelini,Hanwen Liu,Dan Zhu,Xuan Xu,Xin Li,Furui Bai,Xiaopeng Sun,Lin Zha,Yuanfei Huang,Wen Lu,Yanpeng Cao,Du Chen,Zewei He,Sun Anshun,Siliang Tang,Fan Hongfei,Xiang Li,Li Guo,Zhang Wenjie,Zhang Yumei,Qingwen He,Jinghui Qin,Lishan Huang,Yukai Shi,Pengxu Wei,Wushao Wen,Liang Lin,Jun Yu,Guochen Xie,Mengyan Li,Rong Chen,Xiaotong Luo,Chen Hong,Yanyun Qu,Cuihua Li,Zhi-Song Liu,Li-Wen Wang,Chu-Tak Li,Can Zhao,Bowen Li,Chung-Chi Tsai,Shang-Chih Chuang,Joon-Hee Choi,Joon-Soo Kim,Xiaoyun Jiang,Ze Pan,Qunbo Lv,Zheng Tan,Peidong He +103 more
TL;DR: The 3rd NTIRE challenge on single-image super-resolution (restoration of rich details in a low-resolution image) is reviewed with a focus on proposed solutions and results and the state-of-the-art in real-world single image super- resolution.
Journal ArticleDOI
Geometric Back-projection Network for Point Cloud Classification
Shi Qiu,Saeed Anwar,Nick Barnes +2 more
TL;DR: This work uses an idea of error-correcting feedback structure to capture the local features of point clouds comprehensively and applies CNN-based structures in high-level feature spaces to learn local geometric context implicitly.
Posted Content
Dense-Resolution Network for Point Cloud Classification and Segmentation.
Shi Qiu,Saeed Anwar,Nick Barnes +2 more
TL;DR: A novel network named Dense-Resolution Network (DRNet) is proposed for point cloud analysis designed to learn local point features from the point cloud in different resolutions and presents a novel grouping method for local neighborhood searching and an error-minimizing module for capturing local features.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Posted Content
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
TL;DR: This work proposes a Parametric Rectified Linear Unit (PReLU) that generalizes the traditional rectified unit and derives a robust initialization method that particularly considers the rectifier nonlinearities.
Proceedings ArticleDOI
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
TL;DR: In this paper, a Parametric Rectified Linear Unit (PReLU) was proposed to improve model fitting with nearly zero extra computational cost and little overfitting risk, which achieved a 4.94% top-5 test error on ImageNet 2012 classification dataset.
Journal ArticleDOI
Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering
TL;DR: An algorithm based on an enhanced sparse representation in transform domain based on a specially developed collaborative Wiener filtering achieves state-of-the-art denoising performance in terms of both peak signal-to-noise ratio and subjective visual quality.