arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节（Veterans Day），12 日无更新
arXiv 2211.05910eess.IVcs.CV
收藏

移动NPU上高效准确的量化图像超分辨率，移动AI & AIM 2022挑战：报告

Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report

Andrey Ignatov, Radu Timofte, Maurizio Denna, Abdel Younes, Ganzorig Gankhuyag, Jingang Huh, Myeong Kyun Kim, Kihwan Yoon, Hyeon-Cheol Moon, Seungho Lee, Yoonsi… 展开作者

Andrey Ignatov, Radu Timofte, Maurizio Denna, Abdel Younes, Ganzorig Gankhuyag, Jingang Huh, Myeong Kyun Kim, Kihwan Yoon, Hyeon-Cheol Moon, Seungho Lee, Yoonsik Choe, Jinwoo Jeong, Sungjei Kim, Maciej Smyl, Tomasz Latkowski, Pawel Kubik, Michal Sokolski, Yujie Ma, Jiahao Chao, Zhou Zhou, Hongfan Gao, Zhengfeng Yang, Zhenbing Zeng, Zhengyang Zhuge, Chenghua Li, Dan Zhu, Mengdi Sun, Ran Duan, Yan Gao, Lingshun Kong, Long Sun, Xiang Li, Xingdong Zhang, Jiawei Zhang, Yaqi Wu, Jinshan Pan, Gaocheng Yu, Jin Zhang, Feng Zhang, Zhe Ma, Hongbin Wang, Hojin Cho, Steve Kim, Huaen Li, Yanbo Ma, Ziwei Luo, Youwei Li, Lei Yu, Zhihong Wen, Qi Wu, Haoqiang Fan, Shuaicheng Liu, Lize Zhang, Zhikai Zong, Jeremy Kwon, Junxi Zhang, Mengyuan Li, Nianxiang Fu, Guanchen Ding, Han Zhu, Zhenzhong Chen, Gen Li, Yuanfan Zhang, Lei Sun, Dafeng Zhang, Neo Yang, Fitz Liu, Jerry Zhao, Mustafa Ayazoglu, Bahri Batuhan Bilecen, Shota Hirose, Kasidis Arunruangsirilert, Luo Ao, Ho Chun Leung, Andrew Wei, Jie Liu, Qiang Liu, Dahai Yu, Ao Li, Lei Luo, Ce Zhu, Seongmin Hong, Dongwon Park, Joonhee Lee, Byeong Hyun Lee, Seunggyu Lee, Se Young Chun, Ruiyuan He, Xuhao Jiang, Haihang Ruan, Xinjian Zhang, Jing Liu, Garas Gendy, Nabil Sabor, Jingchao Hou, Guanghui He

备注：
arXiv admin note: text overlap with arXiv:2105.07825, arXiv:2105.08826, arXiv:2211.04470, arXiv:2211.03885, arXiv:2211.05256
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

摘要：

图像超分辨率是移动和物联网设备上的常见任务，通常需要放大和增强低分辨率图像和视频帧。虽然在过去已经针对该问题提出了许多解决方案，但是它们通常与具有许多计算和存储器约束的低功率移动NPU不兼容。在这个移动AI挑战中，我们解决了这个问题，并建议参与者设计一个有效的量化图像超分辨率解决方案，可以在移动NPU上展示实时性能。参与者获得了DIV2K数据集和经过训练的INT8模型，以进行高质量的3X图像放大。所有模型的运行时间都在Synaptics VS680智能家居板上进行了评估，该板具有能够加速量化神经网络的专用边缘NPU。所有提出的解决方案都与上述NPU完全兼容，在重建全高清分辨率图像时，显示出高达60 FPS的速率。本文提供了在挑战中开发的所有模型的详细描述。

英文摘要：

Image super-resolution is a common task on mobile and IoT devices, where one often needs to upscale and enhance low-resolution images and video frames. While numerous solutions have been proposed for this problem in the past, they are usually not compatible with low-power mobile NPUs having many computational and memory constraints. In this Mobile AI challenge, we address this problem and propose the participants to design an efficient quantized image super-resolution solution that can demonstrate a real-time performance on mobile NPUs. The participants were provided with the DIV2K dataset and trained INT8 models to do a high-quality 3X image upscaling. The runtime of all models was evaluated on the Synaptics VS680 Smart Home board with a dedicated edge NPU capable of accelerating quantized neural networks. All proposed solutions are fully compatible with the above NPU, demonstrating an up to 60 FPS rate when reconstructing Full HD resolution images. A detailed description of all models developed in the challenge is provided in this paper.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑