Salvato in:
Dettagli Bibliografici
Autori principali: Cancilla, Kylie, Moore, Alexander, Saini, Amar, Carrano, Carmen
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2511.04628
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918189003177984
author Cancilla, Kylie
Moore, Alexander
Saini, Amar
Carrano, Carmen
author_facet Cancilla, Kylie
Moore, Alexander
Saini, Amar
Carrano, Carmen
contents Video quality assessment (VQA) is vital for computer vision tasks, but existing approaches face major limitations: full-reference (FR) metrics require clean reference videos, and most no-reference (NR) models depend on training on costly human opinion labels. Moreover, most opinion-unaware NR methods are image-based, ignoring temporal context critical for video object detection. In this work, we present a scalable, streaming-based VQA model that is both no-reference and opinion-unaware. Our model leverages synthetic degradations of the DAVIS dataset, training a temporal-aware convolutional architecture to predict FR metrics (LPIPS , PSNR, SSIM) directly from degraded video, without references at inference. We show that our streaming approach outperforms our own image-based baseline by generalizing across diverse degradations, underscoring the value of temporal modeling for scalable VQA in real-world vision systems. Additionally, we demonstrate that our model achieves higher correlation with full-reference metrics compared to BRISQUE, a widely-used opinion-aware image quality assessment baseline, validating the effectiveness of our temporal, opinion-unaware approach.
format Preprint
id arxiv_https___arxiv_org_abs_2511_04628
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle NovisVQ: A Streaming Convolutional Neural Network for No-Reference Opinion-Unaware Frame Quality Assessment
Cancilla, Kylie
Moore, Alexander
Saini, Amar
Carrano, Carmen
Computer Vision and Pattern Recognition
Video quality assessment (VQA) is vital for computer vision tasks, but existing approaches face major limitations: full-reference (FR) metrics require clean reference videos, and most no-reference (NR) models depend on training on costly human opinion labels. Moreover, most opinion-unaware NR methods are image-based, ignoring temporal context critical for video object detection. In this work, we present a scalable, streaming-based VQA model that is both no-reference and opinion-unaware. Our model leverages synthetic degradations of the DAVIS dataset, training a temporal-aware convolutional architecture to predict FR metrics (LPIPS , PSNR, SSIM) directly from degraded video, without references at inference. We show that our streaming approach outperforms our own image-based baseline by generalizing across diverse degradations, underscoring the value of temporal modeling for scalable VQA in real-world vision systems. Additionally, we demonstrate that our model achieves higher correlation with full-reference metrics compared to BRISQUE, a widely-used opinion-aware image quality assessment baseline, validating the effectiveness of our temporal, opinion-unaware approach.
title NovisVQ: A Streaming Convolutional Neural Network for No-Reference Opinion-Unaware Frame Quality Assessment
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.04628