Real-Time Quantized Image Super-Resolution on Mobile NPUs, Mobile AI 2021 Challenge: Report

Abstract

Image super-resolution is one of the most popular computer vision problems with many important applications to mobile devices. While many solutions have been proposed for this task, they are usually not optimized even for common smartphone AI hardware, not to mention more constrained smart TV platforms that are often supporting INT8 inference only. To address this problem, we introduce the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based image super-resolution solutions that can demonstrate a real-time performance on mobile or edge NPUs. For this, the participants were provided with the DIV2K dataset and trained quantized models to do an efficient 3X image upscaling. The runtime of all models was evaluated on the Synaptics VS680 Smart Home board with a dedicated NPU capable of accelerating quantized neural networks. The proposed solutions are fully compatible with all major mobile AI accelerators and are capable of reconstructing Full HD images under 40-60 ms while achieving high fidelity results. A detailed description of all models developed in the challenge is provided in this paper.

arXiv commentMobile AI 2021 Workshop and Challenges: https://ai-benchmark.com/workshops/mai/2021/

References in corpus (6)

• Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networks
• RepVGG: Making VGG-style ConvNets Great Again
• Controlling Information Capacity of Binary Neural Network
• AIM 2020 Challenge on Learned Image Signal Processing Pipeline
• T-Basis: a Compact Representation for Neural Networks
• Fast and Accurate Single-Image Depth Estimation on Mobile Devices, Mobile AI 2021 Challenge: Report