Dual Reconstruction Nets for Image Super-Resolution with Gradient Sensitive Loss
arXiv:1809.07099
Abstract
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.
References in corpus (6)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections
- Residual Dense Network for Image Super-Resolution
- Deep Networks for Image Super-Resolution with Sparse Prior
- Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform
- Fast and Accurate Single Image Super-Resolution via Information Distillation Network