研究人员推出了一种新的视频质量度量FDIM，旨在评估标准动态范围（SDR）和高动态范围（HDR）内容下的传统和神经视频编码器。FDIM采用混合方法，结合深度学习进行多尺度特征提取和手工特征，以捕捉广泛的失真。FDIM在超过16,000个视频序列的大型数据集上进行训练，在各种编码器和内容类型上表现出强大的泛化能力，与主观质量评估高度相关。 AI
影响 为评估神经视频编码器提供了一个通用的度量标准，有望加速视频压缩领域的研究和开发。
排序理由 介绍新型视频质量度量的学术论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
Video technology is advancing toward Ultra High Definition (UHD) and High Dynamic Range (HDR), which intensifies the need for higher compression efficiency for these high-specification videos. Beyond advances in traditional codecs, neural video codecs (NVCs) have attracted signif…
arXiv:2604.24123v1 Announce Type: new Abstract: Video technology is advancing toward Ultra High Definition (UHD) and High Dynamic Range (HDR), which intensifies the need for higher compression efficiency for these high-specification videos. Beyond advances in traditional codecs, …
Video technology is advancing toward Ultra High Definition (UHD) and High Dynamic Range (HDR), which intensifies the need for higher compression efficiency for these high-specification videos. Beyond advances in traditional codecs, neural video codecs (NVCs) have attracted signif…