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

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

doi:10.1007/978-3-031-25066-8_5

Cited by 8 publications

(2 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Efficiency in SR. In recent years, the pursuit of efficient SR techniques has gained significant momentum (Li et al, 2022;Ignatov et al, 2023;Li et al, 2023;Conde et al, 2023). Consequently, researchers have introduced streamlined neural architectures (Ignatov et al, 2021), network compression (Wang et al, 2022), reparameterization (Zhang et al, 2021b), and other training strategies to cater to the demand for efficiency.…”

Section: Related Workmentioning

confidence: 99%

Towards Real-Time 4K Image Super-Resolution

Zamfir,

Conde,

Timofte

2023

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

Reconstructing high-resolution (HR) images from low-resolution (LR) inputs poses a significant challenge in image super-resolution (SR). While recent approaches have demonstrated the efficacy of intricate operations customized for various objectives, the straightforward stacking of these disparate operations can result in a substantial computational burden, hampering their practical utility. In response, we introduce SeemoRe, an efficient SR model employing expert mining. Our approach strategically incorporates experts at different levels, adopting a collaborative methodology. At the macro scale, our experts address rank-wise and spatial-wise informative features, providing a holistic understanding. Subsequently, the model delves into the subtleties of rank choice by leveraging a mixture of low-rank experts. By tapping into experts specialized in distinct key factors crucial for accurate SR, our model excels in uncovering intricate intra-feature details. This collaborative approach is reminiscent of the concept of "see more", allowing our model to achieve an optimal performance with minimal computational costs in efficient settings. The source will be publicly made available at https://github. com/eduardzamfir/seemoredetails

show abstract

Section: Related Workmentioning

confidence: 99%

Towards Real-Time 4K Image Super-Resolution

Zamfir,

Conde,

Timofte

2023

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

show abstract

“…Super-resolution is widely used to improve the visual quality of images and videos [23,24,29] displayed on various devices like mobile phones, TVs and so on. In recent years, most media contents are produced and distributed in high resolutions like 720p (HD), 1080p (FHD) and 4k (UHD), and display devices with higher resolutions have become more affordable and popular for the public.…”

Section: Introductionmentioning

confidence: 99%

Baojia Sun, Gongdao Zhang v Shanghai Huili Group Co, Ltd, Shanghai Huili Flooring Products Co, Ltd

Guo¹,

Lin²,

Weng³

2023

Selected Chinese Cases on the CISG

View full text Add to dashboard Cite

In recent years, videos and images in 720p (HD), 1080p (FHD) and 4K (UHD) resolution have become more popular for display devices such as TVs, mobile phones and VR. However, these high resolution images cannot achieve the expected visual effect due to the limitation of the internet bandwidth, and bring a great challenge for super-resolution networks to achieve real-time performance. Following this challenge, we explore multiple efficient network designs, such as pixel-unshuffle, repeat upscaling, and local skip connection removal, and propose a fast and lightweight super-resolution network. Furthermore, by analyzing the applications of the idea of divide-and-conquer in superresolution, we propose assembled convolutions which can adapt convolution kernels according to the input features. Experiments suggest that our method outperforms all the state-of-the-art efficient super-resolution models, and achieves optimal results in terms of runtime and quality.

show abstract