A no-reference video quality predictor for compression and scaling artifacts

Ghadiyaram, Deepti; Chen, Chao; Inguva, Sasi; Kokaram, Anil

doi:10.1109/icip.2017.8296922

Cited by 20 publications

(10 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditional VQA methods consider structures [47,48], gradients [21], motion [22,36], energy [18], saliency [52,54], or natural video statistics [9,28,35,57]. Besides, quality assessment can be achieved by fusion of primary features [8,19].…”

Section: Related Work 21 Video Quality Assessmentmentioning

confidence: 99%

Quality Assessment of In-the-Wild Videos

Jiang

2019

Proceedings of the 27th ACM International Conference on Multimedia

263

245

View full text Add to dashboard Cite

Quality assessment of in-the-wild videos is a challenging problem because of the absence of reference videos and shooting distortions. Knowledge of the human visual system can help establish methods for objective quality assessment of in-the-wild videos. In this work, we show two eminent effects of the human visual system, namely, content-dependency and temporal-memory effects, could be used for this purpose. We propose an objective no-reference video quality assessment method by integrating both effects into a deep neural network. For content-dependency, we extract features from a pre-trained image classification neural network for its inherent content-aware property. For temporal-memory effects, long-term dependencies, especially the temporal hysteresis, are integrated into the network with a gated recurrent unit and a subjectivelyinspired temporal pooling layer. To validate the performance of our method, experiments are conducted on three publicly available inthe-wild video quality assessment databases: KoNViD-1k, CVD2014, and LIVE-Qualcomm, respectively. Experimental results demonstrate that our proposed method outperforms five state-of-the-art methods by a large margin, specifically, 12.39%, 15.71%, 15.45%, and 18.09% overall performance improvements over the second-best method VBLIINDS, in terms of SROCC, KROCC, PLCC and RMSE, respectively. Moreover, the ablation study verifies the crucial role of both the content-aware features and the modeling of temporalmemory effects. The PyTorch implementation of our method is released at https://github.com/lidq92/VSFA. KEYWORDSvideo quality assessment; human visual system; content dependency; temporal-memory effects; in-the-wild videos ACM Reference Format:

show abstract

Section: Related Work 21 Video Quality Assessmentmentioning

confidence: 99%

Quality Assessment of In-the-Wild Videos

Jiang

2019

Proceedings of the 27th ACM International Conference on Multimedia

263

245

View full text Add to dashboard Cite

show abstract

“…5. A follow-on NR VQA called SLEEQ [16] was developed in 2018, which took the NSS concept further. First, as there is no original reference to compare to, they create a "self-referenced" comparator by blurring the compressed (or processed) video by a Gaussian blur, whose standard deviation then becomes a design parameter.…”

Section: No Reference (Nr) Vqasmentioning

confidence: 99%

“…In this paper, we attempt a partial synthesis of some trends in FR and NR VQAs, to formulate what we simply call FastVDO Quality (FVQ). It incorporates lessons from the FR VMAF, the NSS-based assessment concepts in the NR VIIDEO [12], SLEEQ [16], VIDEVAL [18], and RAPIQUE [20], and our own research over the past several years in using learning-based methods in VQA, to create one method that applies to both cases. We provide early indications that this approach can bear fruit for both NR and FR VQA, and may in some cases offer state-of-the-art results in each field.…”

Section: Introductionmentioning

confidence: 99%

VMAF and variants: towards a unified VQA

Topiwala

Dai

Pian

et al. 2021

Applications of Digital Image Processing XLIV

View full text Add to dashboard Cite

Video quality assessment (VQA) is now a fastgrowing subject, beginning to mature in the full reference (FR) case, while the burgeoning no reference (NR) case remains challenging. We investigate variants of the popular VMAF video quality assessment algorithm for the FR case, using support vector regression and feedforward neural networks, and extend it to the NR case, using the same learning architectures, to develop a partially unified framework for VQA. When heavily trained, algorithms such as VMAF perform well on test datasets, with 90%+ match; but predicting performance in the wild is better done by training/testing from scratch, as we do. Even from scratch, we achieve 90%+ performance in FR, with gains over VMAF. And we greatly reduce complexity vs. leading recent NR algorithms, VIDEVAL, RAPIQUE, yet exceed 80% in SRCC. In our preliminary testing, we find the improvements in trainability, while also constraining computational complexity, as quite encouraging, suggesting further study and analysis.

show abstract

“…No-reference quality assessment has been a challenging research topic for decades, and it appears to be increasingly difficult for UGC cases. Table 5 shows the performance of some existing no-reference metrics: BRISQUE [13], NIQE [14], VIIDEO [15], SLEEQ [16], and NIMA [17]. The first four metrics are based on Natural Scene Statistics (NSS), and the last metric is trained by a Convolutional Neural Network model.…”

Section: No-reference Quality Metric For Ugcmentioning

confidence: 99%

Subjective Quality Assessment for YouTube UGC Dataset

Yim¹,

Wang²,

Birkbeck³

et al. 2020

Preprint

View full text Add to dashboard Cite

Due to the scale of social video sharing, User Generated Content (UGC) is getting more attention from academia and industry. To facilitate compression-related research on UGC, YouTube has released a large-scale dataset [1]. The initial dataset only provided videos, limiting its use in quality assessment. We used a crowd-sourcing platform to collect subjective quality scores for this dataset. We analyzed the distribution of Mean Opinion Score (MOS) in various dimensions, and investigated some fundamental questions in video quality assessment, like the correlation between full video MOS and corresponding chunk MOS, and the influence of chunk variation in quality score aggregation.

show abstract

A no-reference video quality predictor for compression and scaling artifacts

Cited by 20 publications

References 18 publications

Quality Assessment of In-the-Wild Videos

Quality Assessment of In-the-Wild Videos

VMAF and variants: towards a unified VQA

Subjective Quality Assessment for YouTube UGC Dataset

Contact Info

Product

Resources

About