Lightweight Image Super-Resolution with Multi-scale Feature Interaction Network
This addresses the need for efficient SISR on mobile devices with limited resources, representing an incremental improvement in lightweight model design.
The paper tackles the problem of high memory consumption in single image super-resolution (SISR) methods by proposing a lightweight multi-scale feature interaction network (MSFIN) that expands the receptive field and uses a recurrent residual channel attention block (RRCAB), achieving comparable performance to state-of-the-art models with a more lightweight design.
Recently, the single image super-resolution (SISR) approaches with deep and complex convolutional neural network structures have achieved promising performance. However, those methods improve the performance at the cost of higher memory consumption, which is difficult to be applied for some mobile devices with limited storage and computing resources. To solve this problem, we present a lightweight multi-scale feature interaction network (MSFIN). For lightweight SISR, MSFIN expands the receptive field and adequately exploits the informative features of the low-resolution observed images from various scales and interactive connections. In addition, we design a lightweight recurrent residual channel attention block (RRCAB) so that the network can benefit from the channel attention mechanism while being sufficiently lightweight. Extensive experiments on some benchmarks have confirmed that our proposed MSFIN can achieve comparable performance against the state-of-the-arts with a more lightweight model.