LCSCNet: Linear Compressing Based Skip-Connecting Network for Image Super-Resolution

TL;DR

LCSCNet is an efficient image super-resolution network that uses linear compressing skip connections and adaptive fusion to improve feature utilization while maintaining parameter economy.

Contribution

The paper introduces LCSCNet, a novel architecture combining linear compressing skip connections with an adaptive fusion strategy for enhanced image super-resolution.

Findings

LCSCNet outperforms state-of-the-art methods in super-resolution tasks.

The linear compressing skip connections improve feature distinction and parameter efficiency.

Adaptive fusion enhances the exploitation of hierarchical features.

Abstract

In this paper, we develop a concise but efficient network architecture called linear compressing based skip-connecting network (LCSCNet) for image super-resolution. Compared with two representative network architectures with skip connections, ResNet and DenseNet, a linear compressing layer is designed in LCSCNet for skip connection, which connects former feature maps and distinguishes them from newly-explored feature maps. In this way, the proposed LCSCNet enjoys the merits of the distinguish feature treatment of DenseNet and the parameter-economic form of ResNet. Moreover, to better exploit hierarchical information from both low and high levels of various receptive fields in deep models, inspired by gate units in LSTM, we also propose an adaptive element-wise fusion strategy with multi-supervised training. Experimental results in comparison with state-of-the-art algorithms validate the effectiveness of LCSCNet.