.png){kind=icon}
Return
Edge-priority-extraction network using re-parameterization for real-time super-resolution
.png){kind=icon}
PRE
AI
DOI：10.1007/s00371-023-03197-y.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Recently, super-resolution (SR) has achieved superior performance with the development of deep learning. However, previous methods usually require considerable computational resources with a large model size, which hinders practical applications. To achieve real-time inference and high quality for SR, this paper presents an edge-priority-extraction network, which is constructed with our proposed edge-priority blocks (EPB). The EPB utilizes multiple branches with edge information to further improve the network representation. Moreover, it can be re-parameterized for efficient inference. For more effective utilization of edge information, this paper also proposes the mix-priority filter with edge extraction of horizontal and vertical priorities to improve the network performance. The filters can adaptively extract the edge information with multi-direction derivatives. The experimental results show that our models can use less computational cost to meet the real-time demand and have a better SR performance than the recent real-time SR models.
Keywords:
Super-resolution
Real-time inference
Edge information
Re-parameterization
Journal
IF:
2.9
Papers:
4.6K
Citations:
6.5K
Organization
Cited Papers
ShareSaveResidual learning based densely connected deep dilated network for joint deblocking and super resolution.png)
APPLIED INTELLIGENCE
APPLIED INTELLIGENCEIF3.5
PREAI
ShareSave
Calcium-modulating cyclophilin ligand regulates membrane trafficking of postsynaptic GABAA receptors
OAAI
OAAIShareSaveShareSaveShareSaveShareSave
View more