Deep neural network for fast and accurate single image super-resolution via channel-attention-based fusion of orientation-aware features: preprint

Du Chen, Zewei He, Yanpeng Cao, Jiangxin Yang, Yanlong Cao, Michael Ying Yang, Siliang Tang, Yueting Zhuang

Research output: Contribution to journalArticleAcademic

24 Downloads (Pure)

Abstract

Recently, Convolutional Neural Networks (CNNs) have been successfully adopted to solve the ill-posed single image super-resolution (SISR) problem. A commonly used strategy to boost the performance of CNN-based SISR models is deploying very deep networks, which inevitably incurs many obvious drawbacks (e.g., a large number of network parameters, heavy computational loads, and difficult model training). In this paper, we aim to build more accurate and faster SISR models via developing better-performing feature extraction and fusion techniques. Firstly, we proposed a novel Orientation-Aware feature extraction and fusion Module (OAM), which contains a mixture of 1D and 2D convolutional kernels (i.e., 5 x 1, 1 x 5, and 3 x 3) for extracting orientation-aware features. Secondly, we adopt the channel attention mechanism as an effective technique to adaptively fuse features extracted in different directions and in hierarchically stacked convolutional stages. Based on these two important improvements, we present a compact but powerful CNN-based model for high-quality SISR via Channel Attention-based fusion of Orientation-Aware features (SISR-CA-OA). Extensive experimental results verify the superiority of the proposed SISR-CA-OA model, performing favorably against the state-of-the-art SISR models in terms of both restoration accuracy and computational efficiency. The source codes will be made publicly available.
Original languageEnglish
Pages (from-to)1-12
Number of pages12
JournalarXiv.org
Publication statusPublished - 9 Dec 2019

Keywords

  • eess.IV
  • cs.CV

Fingerprint

Dive into the research topics of 'Deep neural network for fast and accurate single image super-resolution via channel-attention-based fusion of orientation-aware features: preprint'. Together they form a unique fingerprint.

Cite this