NTIRE 2021 Challenge on Image Deblurring
NTIRE 2021 Challenge on Image Deblurring
复制标题
DOI：
10.1109/cvprw53098.2021.00025
复制
发表时间：
2021-04
期刊：
影响因子：
--
通讯作者：
Seungjun Nah;Sanghyun Son;Suyoung Lee;R. Timofte;Kyoung Mu Lee;Wenhao Wu
中科院分区：
文献类型：
--
作者：
Seungjun Nah;Sanghyun Son;Suyoung Lee;R. Timofte;Kyoung Mu Lee;Wenhao Wu
运动模糊是动态环境中常见的摄影伪影，通常与其他类型的退化一起出现。本文回顾了 NTIRE 2021 图像去模糊挑战赛。在这份挑战报告中，我们描述了挑战细节以及两个竞赛赛道的评估结果以及所提出的解决方案。虽然这两个轨道都旨在从模糊图像中恢复高质量的干净图像，但同时涉及不同的伪影。在轨道 1 中，模糊图像的分辨率较低，而轨道 2 图像以 JPEG 格式压缩。每届比赛分别有 338 名和 238 名参赛者报名，最终测试阶段分别有 18 支和 17 支队伍参赛。获胜方法展示了在联合组合伪像的图像去模糊任务上最先进的性能。
Motion blur is a common photography artifact in dynamic environments that typically comes jointly with the other types of degradation. This paper reviews the NTIRE 2021 Challenge on Image Deblurring. In this challenge report, we describe the challenge specifics and the evaluation results from the 2 competition tracks with the proposed solutions. While both the tracks aim to recover a high-quality clean image from a blurry image, different artifacts are jointly involved. In track 1, the blurry images are in a low resolution while track 2 images are compressed in JPEG format. In each competition, there were 338 and 238 registered participants and in the final testing phase, 18 and 17 teams competed. The winning methods demonstrate the state-of-the-art performance on the image deblurring task with the jointly combined artifacts.