C3DVQA: Full-Reference Video Quality Assessment with 3D Convolutional Neural Network

@article{Xu2020C3DVQAFV,
  title={C3DVQA: Full-Reference Video Quality Assessment with 3D Convolutional Neural Network},
  author={Munan Xu and Junming Chen and Haiqiang Wang and Shan Liu and Ge Li and Zhiqiang Bai},
  journal={ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year={2020},
  pages={4447-4451}
}
  • Munan Xu, Junming Chen, +3 authors Zhiqiang Bai
  • Published 2020
  • Computer Science, Engineering
  • ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Traditional video quality assessment (VQA) methods evaluate localized picture quality and video score is predicted by temporally aggregating frame scores. However, video quality exhibits different characteristics from static image quality due to the existence of temporal masking effects. In this paper, we present a novel architecture, namely C3DVQA, that uses Convolutional Neural Network with 3D kernels (C3D) for full-reference VQA task. C3DVQA combines feature learning and score pooling into… Expand
Deep Learning based Full-reference and No-reference Quality Assessment Models for Compressed UGC Videos
TLDR
The proposed deep learning based video quality assessment (VQA) framework achieves the best performance among the stateof-the-art FR and NR V QA models on the Compressed UGC VQA database and also achieves pretty good performance on the in- the-wild UGC vQA databases. Expand
Learning Graph Convolutional Network for Blind Mesh Visual Quality Assessment
TLDR
A new method for blind mesh visual quality assessment (MVQA) based on a graph convolutional network that addresses the node classification problem to predict the perceived visual quality and investigates several perceptual and visual features to select the most effective combination. Expand
ST-GREED: Space-Time Generalized Entropic Differences for Frame Rate Dependent Video Quality Prediction
TLDR
An objective VQA model called Space-Time GeneRalized Entropic Difference (GREED) is devised which analyzes the statistics of spatial and temporal band-pass video coefficients and achieves state-of-the-art performance on the LIVE-YT-HFR Database when compared with existing V QA models. Expand
On the practical applications of objective quality metrics for stereoscopic 3D imaging
TLDR
This paper introduces an exhaustive analysis regarding the practical applications of objective quality metrics for stereoscopic 3D imaging, and addresses each and every state-of-the-art objective metric in the scientific literature, separately for image and video quality. Expand
Omnidirectional Images as Moving Camera Videos
TLDR
This paper first transforms an omnidirectional image to several video representations using viewing behavior of different users, and then leverage the recent advances in full-reference 2D image/video quality assessment to compute the perceived quality of the panorama. Expand

References

SHOWING 1-10 OF 21 REFERENCES
No-Reference Video Quality Assessment With 3D Shearlet Transform and Convolutional Neural Networks
  • Yuming Li, L. Po, +4 authors K. Cheung
  • Computer Science
  • IEEE Transactions on Circuits and Systems for Video Technology
  • 2016
TLDR
This paper proposes an efficient general-purpose no-reference video quality assessment (VQA) framework that is based on 3D shearlet transform and convolutional neural network and demonstrates that SACONVA performs well in predicting video quality and is competitive with current state-of-the-art full-reference VQA methods and general- Purpose NR-VQ a algorithms. Expand
Deep Video Quality Assessor: From Spatio-Temporal Visual Sensitivity to a Convolutional Neural Aggregation Network
TLDR
A novel full-reference VQA framework named Deep Video Quality Assessor (DeepVQA) is proposed to quantify the spatio-temporal visual perception via a convolutional neural network (CNN) and a convolved neural aggregation network (CNAN) and to manipulate the temporal variation of distortions. Expand
End-to-End Blind Quality Assessment of Compressed Videos Using Deep Neural Networks
TLDR
A Video Multi-task End-to-end Optimized neural Network (V-MEON) that merges the two stages of blind video quality assessment into one, where the feature extractor and the regressor are jointly optimized. Expand
Learning Spatiotemporal Features with 3D Convolutional Networks
TLDR
The learned features, namely C3D (Convolutional 3D), with a simple linear classifier outperform state-of-the-art methods on 4 different benchmarks and are comparable with current best methods on the other 2 benchmarks. Expand
Spatiotemporal Statistics for Video Quality Assessment
TLDR
A new NR-VQA metric based on the spatiotemporal natural video statistics in 3D discrete cosine transform (3D-DCT) domain is proposed, which is universal for multiple types of distortions and robust to different databases. Expand
Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment
TLDR
A deep neural network-based approach to image quality assessment (IQA) that allows for joint learning of local quality and local weights in an unified framework and shows a high ability to generalize between different databases, indicating a high robustness of the learned features. Expand
Motion Tuned Spatio-Temporal Quality Assessment of Natural Videos
TLDR
A general, spatio-spectrally localized multiscale framework for evaluating dynamic video fidelity that integrates both spatial and temporal aspects of distortion assessment and is found to be quite competitive with, and even outperform, algorithms developed and submitted to the VQEG FRTV Phase 1 study, as well as more recent VQA algorithms tested on this database. Expand
ViS3: an algorithm for video quality assessment via analysis of spatial and spatiotemporal slices
TLDR
This work presents a VQA algorithm that estimates quality via separate estimates of perceived degradation due to spatial distortion and joint spatial and temporal distortion, and demonstrates that this algorithm performs well in predicting video quality and is competitive with current state-of-the-art V QA algorithms. Expand
Deep Learning of Human Visual Sensitivity in Image Quality Assessment Framework
  • Jongyoo Kim, S. Lee
  • Computer Science
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
TLDR
A novel convolutional neural networks (CNN) based FR-IQA model, named Deep Image Quality Assessment (DeepQA), where the behavior of the HVS is learned from the underlying data distribution of IQA databases, which achieves the state-of-the-art prediction accuracy among FR- IQA models. Expand
Prediction of Satisfied User Ratio for Compressed Video
TLDR
A method to predict the satisfied-user-ratio (SUR) curves using a machine learning framework that partitions a video clip into local spatial-temporal segments and evaluates the quality of each segment using the VMAF quality index to derive a global one. Expand
...
1
2
3
...