测试6种扩散模型超分辨率效果，发现现有视频质量评估模型都不够准。
How Accurate are Video Quality Models for Diffusion-Based Video Super-Resolution?
- 用主观评价对比6种超分方法在压缩与无损视频上的表现。
- 基于CNN的全参考模型（如LPIPS）相关性最高，但仍有误判。
- 所有模型均无法替代人工评分，适合研究视频质量评估者参考。
近期基于扩散模型的视频超分辨率（VSR）方法展现出良好前景，但其质量评估仍依赖传统视频质量模型。本文通过主观测试，对比六种超分方法（Lanczos、Rhea、SCST、DOVE、SeedVR2、Starlight Mini）在压缩（AV1、DCVC-RT）和无压缩低清视频上的表现，评估其在UHD-1/4K屏幕播放时的质量。使用多种全参考与无参考质量模型进行评估，重点分析序列内性能。结果显示，基于CNN的全参考模型（如LPIPS、DISTS、CVQA-FR）相关性显著优于传统全参考及测试中的无参考模型。其中，多数模型高估了SCST的过锐结果，而VMAF因Starlight Mini引入的空间不一致性而失效。所有测试模型均未达到可替代主观测试的准确度。论文公开了原始视频、重建视频、用户评分与模型打分数据，项目地址：https://github.com/Telecommunication-Telemedia-Assessment/AVT-VQDB-UHD-1-VSR。
原文摘要 · Abstract (English)
Recent video super-resolution (VSR) approaches use deep neural networks to enhance low-quality input videos and recover visual detail, with diffusion-based methods in particular showing promising results. In this paper, we investigate whether existing video quality models can be used to assess the performance of these diffusion-based VSR methods, by comparing model predictions with results from a subjective test. The study compares six upscaling methods (Lanczos, Rhea, SCST, DOVE, SeedVR2, Starlight Mini) applied to both compressed (AV1 and DCVC-RT) and uncompressed low-resolution videos considering the play-out on a UHD-1/4K screen. A range of full- and no-reference quality models are used to assess their applicability to this new type of quality degradation, focusing on within-sequence performance. The results highlight that CNN-based full-reference models, such as LPIPS, DISTS, and CVQA-FR show significantly higher correlation coefficients than both conventional full- as well as the tested no-reference models. Most overestimate the overly sharp results of SCST, with VMAF mainly failing due to spatial inconsistencies introduced by Starlight Mini. None of the tested video quality models reach sufficient accuracy so as to replace complementary subjective testing. The reference, degraded and upscaled videos, as well as the user ratings and model scores are made available with the paper at https://github.com/Telecommunication-Telemedia-Assessment/AVT-VQDB-UHD-1-VSR as open data.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。