Home
Scholarly Works
AIM 2020 Challenge on Learned Image Signal...
Conference

AIM 2020 Challenge on Learned Image Signal Processing Pipeline

Abstract

Abstract This paper reviews the second AIM learned ISP challenge and provides the description of the proposed solutions and results. The participating teams were solving a real-world RAW-to-RGB mapping problem, where to goal was to map the original low-quality RAW images captured by the Huawei P20 device to the same photos obtained with the Canon 5D DSLR camera. The considered task embraced a number of complex computer vision subtasks, such as image demosaicing, denoising, white balancing, color and contrast correction, demoireing, etc. The target metric used in this challenge combined fidelity scores (PSNR and SSIM) with solutions’ perceptual results measured in a user study. The proposed solutions significantly improved the baseline results, defining the state-of-the-art for practical image signal processing pipeline modeling.

Authors

Ignatov A; Timofte R; Zhang Z; Liu M; Wang H; Zuo W; Zhang J; Zhang R; Peng Z; Ren S

Series

Lecture Notes in Computer Science

Volume

12537

Pagination

pp. 152-170

Publisher

Springer Nature

Publication Date

January 1, 2020

DOI

10.1007/978-3-030-67070-2_9

Conference proceedings

Lecture Notes in Computer Science

ISSN

0302-9743
View published work (Non-McMaster Users)

Contact the Experts team