No-Reference Quality Assessment of Variable Frame-Rate Videos Using Temporal Bandpass Statistics

Qi, Zheng; Tu, Zhengzhong; Fan, Yibo; Zeng, Xiaoyang; Bovik, Alan C.

doi:10.1109/icassp43922.2022.9746997

Cited by 4 publications

(2 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we evaluate the performances of our model and various other BVQA models on two UHD-VQA databases. The main models being compared have all been designed for video quality assessment in recent years, and include VSFA [ 38 ], TLVQM [ 39 ], VIDEVAL [ 40 ], GSTVQA [ 18 ], RAPIQUE [ 10 ], ChipQA [ 17 ], NOFU [ 6 ], HEKE [ 9 ] and HFR-BVQA [ 11 ]. Among them, VIDEVAL, ChipQA, TLVQM, RAPIQUE, and VSFA are five VQA models for UGC video.…”

Section: Experimental Resultsmentioning

confidence: 99%

“…First, the VQA task is closely correlated with the perception of distortion information. However, the current BVQA methods [ 9 , 10 , 11 ] usually use backbone convolutional neural networks to extract global spatial distortion features. Such networks are designed for computer vision tasks, such as image classification, focusing more on objects rather than distortions.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Blind Video Quality Assessment for Ultra-High-Definition Video Based on Super-Resolution and Deep Reinforcement Learning

Ying

Pan

Shi

2023

Sensors

View full text Add to dashboard Cite

Ultra-high-definition (UHD) video has brought new challenges to objective video quality assessment (VQA) due to its high resolution and high frame rate. Most existing VQA methods are designed for non-UHD videos—when they are employed to deal with UHD videos, the processing speed will be slow and the global spatial features cannot be fully extracted. In addition, these VQA methods usually segment the video into multiple segments, predict the quality score of each segment, and then average the quality score of each segment to obtain the quality score of the whole video. This breaks the temporal correlation of the video sequences and is inconsistent with the characteristics of human visual perception. In this paper, we present a no-reference VQA method, aiming to effectively and efficiently predict quality scores for UHD videos. First, we construct a spatial distortion feature network based on a super-resolution model (SR-SDFNet), which can quickly extract the global spatial distortion features of UHD videos. Then, to aggregate the spatial distortion features of each UHD frame, we propose a time fusion network based on a reinforcement learning model (RL-TFNet), in which the actor network continuously combines multiple frame features extracted by SR-SDFNet and outputs an action to adjust the current quality score to approximate the subjective score, and the critic network outputs action values to optimize the quality perception of the actor network. Finally, we conduct large-scale experiments on UHD VQA databases and the results reveal that, compared to other state-of-the-art VQA methods, our method achieves competitive quality prediction performance with a shorter runtime and fewer model parameters.

show abstract