arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.21336eess.IV
收藏

针对VMAF NEG图像编解码器优化的分析、问题及鲁棒损失提案

On Optimizing Image Codecs for VMAF NEG: Analysis, Issues, and a Robust Loss Proposal

Huawei Technologies Düsseldorf GmbH(华为技术杜塞尔多夫有限公司);Leibniz University Hannover(汉诺威莱布尼茨大学)

Florian Fingscheidt, Alexander Karabutov, Panqi Jia, Elena Alshina, Jörn Ostermann

AI总结:

本文针对VMAF NEG指标的漏洞提出鲁棒损失方案,以提升图像编解码器的微调效果。

摘要:

VMAF(视频多方法评估融合)指标在图像和视频编码中最近获得了越来越多的关注,因为它被认为与人类感知具有高相关性。这使得在该指标上训练和特别是微调机器学习编解码器变得有趣。然而,VMAF被证明可以被攻击,例如,使图像模糊化可以导致VMAF质量提升,同时降低人类感知质量。一种称为VMAF NEG的VMAF版本被设计得更鲁棒,因此应该更适合编解码器的微调。在本文中,我们的贡献有三个方面。首先,我们识别并分析VMAF NEG仍存在的对攻击的漏洞,特别是针对使用VMAF NEG进行图像编解码器微调的攻击。第二,为了利用VMAF NEG与人类感知的高相关性,我们提出一个包含VMAF NEG的鲁棒损失,用于微调编码器或解码器。第三,我们通过提供一些图像示例的感知印象来支持我们的定量客观结果。

英文摘要:

The VMAF (video multi-method assessment fusion) metric for image and video coding recently gained more and more popularity as it is supposed to have a high correlation with human perception. This makes training and particularly fine-tuning of machine-learned codecs on this metric interesting. However, VMAF is shown to be attackable in a way that, e.g., unsharpening an image can lead to a gain in VMAF quality while decreasing the quality in human perception. A particular version of VMAF called VMAF NEG has been designed to be more robust against such attacks and therefore it should be more useful for fine-tuning of codecs. In this paper, our contributions are threefold. First, we identify and analyze the still existing vulnerability of VMAF NEG towards attacks, particulary towards the attack that consists in employing VMAF NEG for image codec fine-tuning. Second, to benefit from VMAF NEG's high correlation with human perception, we propose a robust loss including VMAF NEG for fine-tuning either the encoder or the decoder. Third, we support our quantitative objective results by providing perceptive impressions of some image examples.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑