A Heterogeneous Group CNN for Image Super-Resolution

• Published in: IEEE transaction on neural networks and learning systems Vol. 35; no. 5; pp. 6507 - 6519
• Main Authors: Tian, Chunwei, Zhang, Yanning, Zuo, Wangmeng, Lin, Chia-Wen, Zhang, David, Yuan, Yixuan
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.05.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Computer architecture; Convolution; Convolutional neural networks; Feature extraction; Heterogeneous group convolutional architecture; Image quality; Image resolution; image super-resolution (SR); multilevel enhancement mechanism; Network architecture; Neural networks; Qualitative analysis; Superresolution; symmetric architecture; Training
• ISSN: 2162-237X; 2162-2388
• DOI: 10.1109/TNNLS.2022.3210433

Convolutional neural networks (CNNs) have obtained remarkable performance via deep architectures. However, these CNNs often achieve poor robustness for image super-resolution (SR) under complex scenes. In this article, we present a heterogeneous group SR CNN (HGSRCNN) via leveraging structure information of different types to obtain a high-quality image. Specifically, each heterogeneous group block (HGB) of HGSRCNN uses a heterogeneous architecture containing a symmetric group convolutional block and a complementary convolutional block in a parallel way to enhance the internal and external relations of different channels for facilitating richer low-frequency structure information of different types. To prevent the appearance of obtained redundant features, a refinement block (RB) with signal enhancements in a serial way is designed to filter useless information. To prevent the loss of original information, a multilevel enhancement mechanism guides a CNN to achieve a symmetric architecture for promoting expressive ability of HGSRCNN. Besides, a parallel upsampling mechanism is developed to train a blind SR model. Extensive experiments illustrate that the proposed HGSRCNN has obtained excellent SR performance in terms of both quantitative and qualitative analysis. Codes can be accessed at https://github.com/hellloxiaotian/HGSRCNN .