论文标题
Flolpips：定制视频质量指标用于框架插入
FloLPIPS: A Bespoke Video Quality Metric for Frame Interpoation
论文作者
论文摘要
视频框架插值（VFI）是许多视频处理应用程序的有用工具。最近，它也已应用于视频压缩域中，以增强常规视频编解码器和基于学习的压缩体系结构。尽管近年来，人们对增强框架插值算法的发展的重点越来越大，但插值内容的感知质量评估仍然是一个开放的研究领域。在本文中，我们为VFI，Flolpips提供了定制的完整参考视频质量指标，该指标基于流行的感知图像质量指标LPIP，该指标捕获了提取的图像特征空间中的感知降解。为了提高LPIP的性能用于评估插值内容，我们通过使用时间失真（通过比较光流）来对特征差异图进行加权来重新设计其空间特征聚合步骤。在BVI-VFI数据库上进行了评估，该数据库包含180个带有各种框架插值伪像的测试序列，Flolpips显示出优异的相关性能（具有统计意义），主观地面真相超过12位流行的质量评估者。为了促进VFI质量评估的进一步研究，我们的代码可在https://danier97.github.io/flolpips上公开获得。
Video frame interpolation (VFI) serves as a useful tool for many video processing applications. Recently, it has also been applied in the video compression domain for enhancing both conventional video codecs and learning-based compression architectures. While there has been an increased focus on the development of enhanced frame interpolation algorithms in recent years, the perceptual quality assessment of interpolated content remains an open field of research. In this paper, we present a bespoke full reference video quality metric for VFI, FloLPIPS, that builds on the popular perceptual image quality metric, LPIPS, which captures the perceptual degradation in extracted image feature space. In order to enhance the performance of LPIPS for evaluating interpolated content, we re-designed its spatial feature aggregation step by using the temporal distortion (through comparing optical flows) to weight the feature difference maps. Evaluated on the BVI-VFI database, which contains 180 test sequences with various frame interpolation artefacts, FloLPIPS shows superior correlation performance (with statistical significance) with subjective ground truth over 12 popular quality assessors. To facilitate further research in VFI quality assessment, our code is publicly available at https://danier97.github.io/FloLPIPS.
