4.5 Article Proceedings Paper

Learning a self-supervised tone mapping operator via feature contrast masking loss

期刊

COMPUTER GRAPHICS FORUM
卷 41, 期 2, 页码 71-84

出版社

WILEY
DOI: 10.1111/cgf.14459

关键词

CCS Concepts; center dot Computing methodologies -> Computational photography; Neural networks; Image processing

资金

  1. European Research Council (ERC) under the European Union [682080]

向作者/读者索取更多资源

This paper introduces a learning-based self-supervised tone mapping operator that can be trained for each HDR image without any data labeling. The key novelty of this approach is the carefully designed loss function based on contrast perception, which allows for direct comparison of content in HDR and tone mapped images. Extensive studies and exploration of parameters demonstrate that this solution outperforms existing approaches in both objective and subjective metrics.
High Dynamic Range (HDR) content is becoming ubiquitous due to the rapid development of capture technologies. Nevertheless, the dynamic range of common display devices is still limited, therefore tone mapping (TM) remains a key challenge for image visualization. Recent work has demonstrated that neural networks can achieve remarkable performance in this task when compared to traditional methods, however, the quality of the results of these learning-based methods is limited by the training data. Most existing works use as training set a curated selection of best-performing results from existing traditional tone mapping operators (often guided by a quality metric), therefore, the quality of newly generated results is fundamentally limited by the performance of such operators. This quality might be even further limited by the pool of HDR content that is used for training. In this work we propose a learning-based self-supervised tone mapping operator that is trained at test time specifically for each HDR image and does not need any data labeling. The key novelty of our approach is a carefully designed loss function built upon fundamental knowledge on contrast perception that allows for directly comparing the content in the HDR and tone mapped images. We achieve this goal by reformulating classic VGG feature maps into feature contrast maps that normalize local feature differences by their average magnitude in a local neighborhood, allowing our loss to account for contrast masking effects. We perform extensive ablation studies and exploration of parameters and demonstrate that our solution outperforms existing approaches with a single set of fixed parameters, as confirmed by both objective and subjective metrics.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.5
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据