Dual Reconstruction Nets for Image Super-Resolution with Gradient Sensitive Loss

By Yong Guo, Qi Chen, Junzhou Huang, Yanwu Xu, Jiezhang Cao, Peilin Zhao, Mingkui Tan. 2018

17 citations recorded by the source corpus.

Deep neural networks have exhibited promising performance in image super-resolution (SR) due to the power in learning the non-linear mapping from low-resolution (LR) images to high-resolution (HR) images. However, most deep learning methods employ feed-forward architectures, and thus the dependencies between LR and HR images are not fully exploited, leading to limited learning performance. Moreover, most deep learning based SR methods apply the pixel-wise reconstruction error as the loss, which, however, may fail to capture high-frequency information and produce perceptually unsatisfying results, whilst the recent perceptual loss relies on some pre-trained deep model and they may not generalize well. In this paper, we introduce a mask to separate the image into low- and high-frequency parts based on image gradient magnitude, and then devise a gradient sensitive loss to well capture the structures in the image without sacrificing the recovery of low-frequency content. Moreover, by investigating the duality in SR, we develop a dual reconstruction network (DRN) to improve the SR performance. We provide theoretical analysis on the generalization performance of our method and demonstrate its effectiveness and superiority with thorough experiments.

Subfields: Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Mingkui Tan
2. Jian Chen
3. Yong Guo
4. Steven C. H. Hoi
5. Jingdong Wang
6. Peilin Zhao
7. Junzhou Huang
8. Ming-Hsuan Yang

In Media Technology

1. Yong Guo
2. Peilin Zhao
3. Qi Chen
4. Jingdong Wang
5. Steven C. H. Hoi
6. Junzhou Huang
7. Zhenhao He
8. Yongsheng Luo

Citations in the corpus

• Hierarchical Neural Architecture Search for Single Image Super-Resolution (2020, background): “I MAGE super-resolution (SR) is an important computer vision task that aims at designing effective models to reconstruct the high-resolution (HR) images from the low-resolution (LR) images [1]–[6].”
• Deep Learning for Image Super-Resolution: A Survey (2019, background): “In practice, researchers often combine multiple loss functions by weighted average [8], [25], [27], [46], [141] for constraining different aspects of the generation process, especially for distortion-perception tradeoff [25], [103], [142], [143], [144].”
• Discrimination-Aware Network Pruning for Deep Model Compression (2020, background): “image generation [5], [13], [15], video analysis [63], [76], [83] and many other areas [14], [20].”
• Closed-Loop Matters: Dual Regression Networks for Single Image Super-Resolution (2020, methodology): “Based on DNNs, many methods have been proposed to improve SR performance [51, 26, 10, 12, 49].”
• NAT: Neural Architecture Transformer for Accurate and Compact Architectures (2019, background): “…networks (DNNs) [25] have been producing state-of-the-art results in many challenging tasks including image classification [12, 23, 43, 60, 61, 18, 11, 56], face recognition [39, 44, 59], brain signal processing [34, 35], video analysis [48, 53, 52] and many other areas [58, 57, 24, 3, 10, 9, 4].”