A very lightweight image super-resolution network.
Sci Rep
; 14(1): 13850, 2024 Jun 15.
Article
en En
| MEDLINE
| ID: mdl-38879679
ABSTRACT
Recently, ConvNeXt and blueprint separable convolution (BSConv) constructed from standard ConvNet modules have demonstrated competitive performance in advanced computer vision tasks. This paper proposes an efficient model (BCRN) based on BSConv and the ConvNeXt residual structure for single image super-resolution, which achieves superior performance with very low parametric numbers. Specifically, the residual block (BCB) of the BCRN utilizes the ConvNeXt residual structure and BSConv to significantly reduce the number of parameters. Within the residual block, enhanced spatial attention and contrast-aware channel attention modules are simultaneously introduced to prioritize valuable features within the network. Multiple residual blocks are then stacked to form the backbone network, with Dense connections utilized between them to enhance feature utilization. Our model boasts extremely low parameters compared to other state-of-the-art lightweight models, while experimental results on benchmark datasets demonstrate its excellent performance. The code will be available at https//github.com/kptx666/BCRN .
Texto completo:
1
Colección:
01-internacional
Base de datos:
MEDLINE
Idioma:
En
Revista:
Sci Rep
Año:
2024
Tipo del documento:
Article
País de afiliación:
China
Pais de publicación:
Reino Unido