Recently, great progress has been made in single-image super-resolution (SISR) based on deep learning technology. However, the existing methods usually require a large computational cost. Meanwhile, the activation function will cause some features of the intermediate layer to be lost. Therefore, it is a challenge to make the model lightweight while reducing the impact of intermediate feature loss on the reconstruction quality. In this paper, we propose a Feature Interaction Weighted Hybrid Network (FIWHN) to alleviate the above problem. Specifically, FIWHN consists of a series of novel Wide-residual Distillation Interaction Blocks (WDIB) as the backbone, where every third WDIBs form a Feature shuffle Weighted Group (FSWG) by mutual information mixing and fusion. In addition, to mitigate the adverse effects of intermediate feature loss on the reconstruction results, we introduced a well-designed Wide Convolutional Residual Weighting (WCRW) and Wide Identical Residual Weighting (WIRW) units in WDIB, and effectively cross-fused features of different finenesses through a Wide-residual Distillation Connection (WRDC) framework and a Self-Calibrating Fusion (SCF) unit. Finally, to complement the global features lacking in the CNN model, we introduced the Transformer into our model and explored a new way of combining the CNN and Transformer. Extensive quantitative and qualitative experiments on low-level and high-level tasks show that our proposed FIWHN can achieve a good balance between performance and efficiency, and is more conducive to downstream tasks to solve problems in low-pixel scenarios.
翻译:最近,在以深层学习技术为基础的单一图像超分辨率(SISR)方面取得了很大进展。然而,现有方法通常需要大量的计算成本。同时,启动功能将使中间层的某些特征丢失。因此,在降低中间特征损失对重建质量的不利影响的同时,使模型轻量体减少中间特征损失对中间特征损失的影响是一项挑战。在本文件中,我们提出一个设计完善的大型革命残留网(FIWWWHN)以缓解上述问题。具体地说,FIWWHN由一系列全新的宽度蒸馏互动区(WIDIB)组成,作为骨干,每三分之一的WDIBS通过相互信息混合和融合,形成一个特质重组。 此外,为了减轻中间特征损失对重建质量的影响,我们推出了一个设计完善的大型革命残留(WCRWRW)和广度模型(WIWRWA)的低度模型(WIDIB)组成了一系列新的宽度质量淡度互动区段(WIDIB)作为骨干,并且有效地交叉利用不同精度的精度特征,通过一个宽度结构化框架和不断升级的模型(IFISDFIS),最后展示(IFIDFID) 和FIFL-S-FID-S-S-S-S-S-S-dexxxxxxxxxxxx) 的模型展示一个新的模型,可以展示一个新的格式和深度框架和不断展示一个新的模型,以展示式框架和不断进式框架和FIFIFIFIFIFIFIFIS-FID-S-S-FDxxxxxxxxxxx。