Residual trio feature network for efficient super-resolution

Autor: Junfeng Chen, Mao Mao, Azhu Guan, Altangerel Ayush
Jazyk: angličtina
Rok vydání: 2024
Předmět:
Zdroj: Complex & Intelligent Systems, Vol 11, Iss 1, Pp 1-12 (2024)
Druh dokumentu: article
ISSN: 2199-4536
2198-6053
DOI: 10.1007/s40747-024-01624-8
Popis: Abstract Deep learning-based approaches have demonstrated impressive performance in single-image super-resolution (SISR). Efficient super-resolution compromises the reconstructed image’s quality to have fewer parameters and Flops. Ensured efficiency in image reconstruction and improved reconstruction quality of the model are significant challenges. This paper proposes a trio branch module (TBM) based on structural reparameterization. TBM achieves equivalence transformation through structural reparameterization operations, which use a complex network structure in the training phase and convert it to a more lightweight structure in the inference, achieving efficient inference while maintaining accuracy. Based on the TBM, we further design a lightweight version of the enhanced spatial attention mini (ESA-mini) and the residual trio feature block (RTFB). Moreover, the multiple RTFBs are combined to construct the residual trio network (RTFN). Finally, we introduce a localized contrast loss for better applicability to the super-resolution task, which enhances the reconstruction quality of the super-resolution model. Experiments show that the RTFN framework proposed in this paper outperforms other state-of-the-art efficient super-resolution methods in terms of inference speed and reconstruction quality.
Databáze: Directory of Open Access Journals
Externí odkaz: