Single-Image Super Resolution (SISR) is a classical computer vision problem and it has been studied for over decades. With the recent success of deep learning methods, recent work on SISR focuses solutions with deep learning methodologies and achieves state-of-the-art results. However most of the state-of-the-art SISR methods contain millions of parameters and layers, which limits their practical applications. In this paper, we propose a hardware (Synaptics Dolphin NPU) limitation aware, extremely lightweight quantization robust real-time super resolution network (XLSR). The proposed model's building block is inspired from root modules for Image classification. We successfully applied root modules to SISR problem, further more to make the model uint8 quantization robust we used Clipped ReLU at the last layer of the network and achieved great balance between reconstruction quality and runtime. Furthermore, although the proposed network contains 30x fewer parameters than VDSR its performance surpasses it on Div2K validation set. The network proved itself by winning Mobile AI 2021 Real-Time Single Image Super Resolution Challenge.

本文提出了一种硬件限制感知、极其轻量级、量化鲁棒、实时超分辨率网络 (XLSR)，它是一种受到 root 模块的启发，旨在解决单图像超分辨率问题的建模方法，并在 Div2K 验证集上取得了超过 VDSR 的成果，在 2021 年移动 AI 实时单图像超分辨率挑战赛中得胜。

极轻量化鲁棒实时单图像超分辨率算法在移动设备上的应用