PIRM Challenge on Perceptual Image Enhancement on Smartphones: Report

Ignatov, Andrey; Timofte, Radu; Van Vu, Thang; Minh Luu, Tung; X Pham, Trung; Van Nguyen, Cao; Kim, Yongwoo; Choi, Jae-Seok; Kim, Munchurl; Huang, Jie; Ran, Jiewen; Xing, Chen; Zhou, Xingguang; Zhu, Pengfei; Geng, Mingrui; Li, Yawei; Agustsson, Eirikur; Gu, Shuhang; Van Gool, Luc; de Stoutz, Etienne; Kobyshev, Nikolay; Nie, Kehui; Zhao, Yan; Li, Gen; Tong, Tong; Gao, Qinquan; Hanwen, Liu; Navarrete Michelini, Pablo; Dan, Zhu; Fengshuo, Hu; Hui, Zheng; Wang, Xiumei; Deng, Lirui; Meng, Rang; Qin, Jinghui; Shi, Yukai; Wen, Wushao; Lin, Liang; Feng, Ruicheng; Wu, Shixiang; Dong, Chao; Qiao, Yu; Vasu, Subeesh; Thekke Madam, Nimisha; Kandula, Praveen; Rajagopalan, A. N.; Liu, Jie; Jung, Cheolkon

Andrey Ignatov, Radu Timofte, Thang Van Vu, Tung Minh Luu, Trung X Pham, Cao Van Nguyen, Yongwoo Kim, Jae-Seok Choi, Munchurl Kim, Jie Huang, Jiewen Ran, Chen Xing, Xingguang Zhou, Pengfei Zhu, Mingrui Geng, Yawei Li, Eirikur Agustsson, Shuhang Gu, Luc Van Gool, Etienne de Stoutz, Nikolay Kobyshev, Kehui Nie, Yan Zhao, Gen Li, Tong Tong, Qinquan Gao, Liu Hanwen, Pablo Navarrete Michelini, Zhu Dan, Hu Fengshuo, Zheng Hui, Xiumei Wang, Lirui Deng, Rang Meng, Jinghui Qin, Yukai Shi, Wushao Wen, Liang Lin, Ruicheng Feng, Shixiang Wu, Chao Dong, Yu Qiao, Subeesh Vasu, Nimisha Thekke Madam, Praveen Kandula, A. N. Rajagopalan, Jie Liu, Cheolkon Jung; Proceedings of the European Conference on Computer Vision (ECCV) Workshops, 2018, pp. 0-0

Abstract

This paper reviews the first challenge on efficient perceptual image enhancement with the focus on deploying deep learning models on smartphones. The challenge consisted of two tracks. In the first one, participants were solving the classical image super-resolution problem with a bicubic downscaling factor of 4. The second track was aimed at real-world photo enhancement, and the goal was to map low-quality photos from the iPhone 3GS device to the same photos captured with a DSLR camera. The target metric used in this challenge combined the runtime, PSNR scores and solutions’ perceptual results measured in the user study. To ensure the efficiency of the submitted models, we additionally measured their runtime and memory requirements on Android smartphones. The proposed solutions significantly improved baseline results defining the state-of-the-art for image enhancement on smartphones.

Related Material

[pdf] [arXiv]

[bibtex]

@InProceedings{Ignatov_2018_ECCV_Workshops,
author = {Ignatov, Andrey and Timofte, Radu and Van Vu, Thang and Minh Luu, Tung and X Pham, Trung and Van Nguyen, Cao and Kim, Yongwoo and Choi, Jae-Seok and Kim, Munchurl and Huang, Jie and Ran, Jiewen and Xing, Chen and Zhou, Xingguang and Zhu, Pengfei and Geng, Mingrui and Li, Yawei and Agustsson, Eirikur and Gu, Shuhang and Van Gool, Luc and de Stoutz, Etienne and Kobyshev, Nikolay and Nie, Kehui and Zhao, Yan and Li, Gen and Tong, Tong and Gao, Qinquan and Hanwen, Liu and Navarrete Michelini, Pablo and Dan, Zhu and Fengshuo, Hu and Hui, Zheng and Wang, Xiumei and Deng, Lirui and Meng, Rang and Qin, Jinghui and Shi, Yukai and Wen, Wushao and Lin, Liang and Feng, Ruicheng and Wu, Shixiang and Dong, Chao and Qiao, Yu and Vasu, Subeesh and Thekke Madam, Nimisha and Kandula, Praveen and Rajagopalan, A. N. and Liu, Jie and Jung, Cheolkon},
title = {PIRM Challenge on Perceptual Image Enhancement on Smartphones: Report},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV) Workshops},
month = {September},
year = {2018}
}