How Accurate are Video Quality Models for Diffusion-Based Video Super-Resolution?

• URL: http://arxiv.org/abs/2605.25940v1
• Date: Mon, 25 May 2026 15:18:22 GMT
• Title: How Accurate are Video Quality Models for Diffusion-Based Video Super-Resolution?
• Abstract summary: We investigate whether existing video quality models can be used to assess the performance of diffusion-based VSR methods.<n>We compare model predictions with results from a subjective test.<n>None of the tested video quality models reach sufficient accuracy so as to replace complementary subjective testing.
• Score: 38.486900599288084
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• CompressedVQA-AEV: Full-Reference and No-Reference Quality Assessment Models for Asymmetric Encoded Videos [51.44042801857041]
  This report presents our solutions to the QoMEX 2026 Grand Challenge on Video Quality Assessment for Asymmetric Encoded Videos.<n>It comprises a full-reference (FR) model, CompressedVQA-AEV-FR, and a no-reference (NR) model, CompressedVQA-AEV-NR.<n>For the NR setting, our model employs complementary frame-level encoders based on SigLIP2 and Swin-B, followed by temporal mean pooling and cross-fold ensembling to estimate perceptual quality without reference data.
  arXiv  Detail & Related papers  (2026-07-06T02:23:39Z)
• Rethinking Diffusion Model-Based Video Super-Resolution: Leveraging Dense Guidance from Aligned Features [51.5076190312734]
  Video Super-Resolution approaches suffer from error accumulation, spatial artifacts, and a trade-off between perceptual quality and fidelity.<n>We propose a novelly Guided diffusion model with Aligned Features for Video Super-Resolution (DGAF-VSR)<n>Experiments on synthetic and real-world datasets demonstrate that DGAF-VSR surpasses state-of-the-art methods in key aspects of VSR.
  arXiv  Detail & Related papers  (2025-11-21T03:40:45Z)
• CAMP-VQA: Caption-Embedded Multimodal Perception for No-Reference Quality Assessment of Compressed Video [9.172799792564009]
  We propose CAMP-VQA, a novel NR-VQA framework that exploits the semantic understanding capabilities of large models.<n>Our approach introduces a quality-aware video metadata mechanism that integrates key fragments extracted from inter-frame variations.<n>Our model consistently outperforms existing NR-VQA methods, achieving improved accuracy without the need for costly manual fine-grained annotations.
  arXiv  Detail & Related papers  (2025-11-10T16:37:47Z)
• Subjective and Objective Quality Assessment of Banding Artifacts on Compressed Videos [55.09949353783613]
  Noticeable banding artifacts can severely impact the perceptual quality of videos viewed on a high-end HDTV or high-resolution screen.<n>We have created a first-of-a-kind open video dataset, dubbed LIVE-YT-Banding, which consists of 160 videos generated by four different compression parameters.<n>A total of 7,200 subjective opinions are collected from a cohort of 45 human subjects.
  arXiv  Detail & Related papers  (2025-08-12T07:42:56Z)
• Unsupervised Video Anomaly Detection with Diffusion Models Conditioned on Compact Motion Representations [17.816344808780965]
  unsupervised video anomaly detection (VAD) problem involves classifying each frame in a video as normal or abnormal, without any access to labels. To accomplish this, proposed method employs conditional diffusion models, where the input data is features extracted from pre-trained network. Our method utilizes a data-driven threshold and considers a high reconstruction error as an indicator of anomalous events.
  arXiv  Detail & Related papers  (2023-07-04T07:36:48Z)
• CONVIQT: Contrastive Video Quality Estimator [63.749184706461826]
  Perceptual video quality assessment (VQA) is an integral component of many streaming and video sharing platforms. Here we consider the problem of learning perceptually relevant video quality representations in a self-supervised manner. Our results indicate that compelling representations with perceptual bearing can be obtained using self-supervised learning.
  arXiv  Detail & Related papers  (2022-06-29T15:22:01Z)
• Diffusion Probabilistic Modeling for Video Generation [17.48026395867434]
  Denoising diffusion probabilistic models are a promising new class of generative models that are competitive with GANs on perceptual metrics. Inspired by recent advances in neural video compression, we use denoising diffusion models to generate a residual baseline to a deterministic next-frame prediction. We find significant improvements in terms of perceptual quality on all data and improvements in terms of frame forecasting for complex high-resolution videos.
  arXiv  Detail & Related papers  (2022-03-16T03:52:45Z)
• FOVQA: Blind Foveated Video Quality Assessment [1.4127304025810108]
  We develop a no-reference (NR) foveated video quality assessment model, called FOVQA. It is based on new models of space-variant natural scene statistics (NSS) and natural video statistics (NVS) FOVQA achieves state-of-the-art (SOTA) performance on the new 2D LIVE-FBT-FCVR database.
  arXiv  Detail & Related papers  (2021-06-24T21:38:22Z)
• Study on the Assessment of the Quality of Experience of Streaming Video [117.44028458220427]
  In this paper, the influence of various objective factors on the subjective estimation of the QoE of streaming video is studied. The paper presents standard and handcrafted features, shows their correlation and p-Value of significance. We take SQoE-III database, so far the largest and most realistic of its kind.
  arXiv  Detail & Related papers  (2020-12-08T18:46:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.