Fully 1 × 1 Convolutional Network for Lightweight Image Super-resolution

Abstract Deep convolutional neural networks, particularly large models with large kernels (3 × 3 or more), have achieved significant progress in single image super-resolution (SISR) tasks. However, the heavy computational footprint of such models prevents their deployment in real-time, resource-constrained environments. Conversely, 1 × 1 convolutions have substantial computational efficiency, but struggle with aggregating local spatial representations, which is an essential capability for SISR models. In response to this dichotomy, we propose to harmonize the merits of both 3 × 3 and 1 × 1 kernels, and exploit their great potential for lightweight SISR tasks. Specifically, we propose a simple yet effective fully 1 × 1 convolutional network, named shift-Conv-based network (SCNet). By incorporating a parameter-free spatial-shift operation, the fully 1 × 1 convolutional network is equipped with a powerful representation capability and impressive computational efficiency. Extensive experiments demonstrate that SCNets, despite their fully 1 × 1 convolutional structure, consistently match or even surpass the performance of existing lightweight SR models that employ regular convolutions. The code and pretrained models can be found at https://github.com/Aitical/SCNet .