Image Super-Resolution Using Very Deep Residual Channel Attention Networks
Convolutional neural network (CNN) depth is of crucial importance for image super-resolution (SR). However, we observe that deeper networks for image SR are more difficult to train. The low-resolution inputs and features contain abundant low-frequency information, which is treated equally across channels, hence hindering the representational ability of CNNs. To solve these problems, we propose the very deep residual channel attention networks (RCAN). Specifically, we propose a residual in residual (RIR) structure to form very deep network, which consists of several residual groups with long skip connections. Each residual group contains some residual blocks with short skip connections. Meanwhile, RIR allows abundant low-frequency information to be bypassed through multiple skip connections, making the main network focus on learning high-frequency information. Furthermore, we propose a channel attention mechanism to adaptively rescale channel-wise features by considering interdependencies among channels. Extensive experiments show that our RCAN achieves better accuracy and visual improvements against state-of-the-art methods.
Code (20)
Tasks
Image Super-ResolutionSuper-ResolutionSimilar Papers 제목 키워드 기반
Single Image Super-Resolution using Residual Channel Attention Network
Single Image Super-resolution refers to the method of converting one low-resolution image to its high-resolution counterpart which is a very challenging task since a low-resolution image can yield several possible high-r…
Face RecognitionImage Super-ResolutionSuper-ResolutionResidual Channel Attention Generative Adversarial Network for Image Super-Resolution and Noise Reduction
Image super-resolution is one of the important computer vision techniques aiming to reconstruct high-resolution images from corresponding low-resolution ones. Most recently, deep learning-based approaches have been demon…
Generative Adversarial NetworkImage Super-ResolutionSuper-ResolutionAn Effective Single-Image Super-Resolution Model Using Squeeze-and-Excitation Networks
Recent works on single-image super-resolution are concentrated on improving performance through enhancing spatial encoding between convolutional layers. In this paper, we focus on modeling the correlations between channe…
Image Super-ResolutionSuper-ResolutionSuper-Resolution Reconstruction from Bayer-Pattern Spike Streams
Spike camera is a neuromorphic vision sensor that can capture highly dynamic scenes by generating a continuous stream of binary spikes to represent the arrival of photons at very high temporal resolution. Equipped wi…
Motion EstimationSuper-ResolutionHybrid Residual Attention Network for Single Image Super Resolution
The extraction and proper utilization of convolution neural network (CNN) features have a significant impact on the performance of image super-resolution (SR). Although CNN features contain both the spatial and channel i…
Image Super-ResolutionSuper-Resolution