Reference-Free DIBR-Synthesized Video Quality Metric in Spatial and Temporal Domains

Wang, Guangcheng; Wang, Zhongyuan; Gu, Ke; Jiang, Kui; Zheng, He

doi:10.1109/tcsvt.2021.3074181

Cited by 22 publications

(5 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The competing IQA metrics designed for natural images include PSNR, SSIM (Wang et al, 2004 ), IW-SSIM (Wang and Li, 2011 ), ADD-SSIM (Gu et al, 2016 ), PSIM (Gu et al, 2017a ), NIQE (Mittal et al, 2013 ), ILNIQE (Zhang et al, 2015 ), ARISM (Gu et al, 2015 ), and BIQME (Gu et al, 2018b ). The competing IQA methods devised for DIBR-synthesized images consist of MW-PSNR (Dragana et al, 2015b ), MP-PSNR (Dragana et al, 2015a ), MP-PSNR-reduce (Dragana et al, 2016 ), NIQSV+ (Tian et al, 2018 ), APT (Gu et al, 2018a ), CLGM (Yue et al, 2019 ), STD (Wang et al, 2021 ), LMS (Zhou et al, 2019 ), IDEA (Li et al, 2021b ), GANs-NRM (Ling et al, 2020 ), and OUT (Jakhetiya et al, 2019 ).…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

DIBR-Synthesized Image Quality Assessment With Texture and Depth Information

et al. 2021

Self Cite

View full text Add to dashboard Cite

Accurately predicting the quality of depth-image-based-rendering (DIBR) synthesized images is of great significance in promoting DIBR techniques. Recently, many DIBR-synthesized image quality assessment (IQA) algorithms have been proposed to quantify the distortion that existed in texture images. However, these methods ignore the damage of DIBR algorithms on the depth structure of DIBR-synthesized images and thus fail to accurately evaluate the visual quality of DIBR-synthesized images. To this end, this paper presents a DIBR-synthesized image quality assessment metric with Texture and Depth Information, dubbed as TDI. TDI predicts the quality of DIBR-synthesized images by jointly measuring the synthesized image's colorfulness, texture structure, and depth structure. The design principle of our TDI includes two points: (1) DIBR technologies bring color deviation to DIBR-synthesized images, and so measuring colorfulness can effectively predict the quality of DIBR-synthesized images. (2) In the hole-filling process, DIBR technologies introduce the local geometric distortion, which destroys the texture structure of DIBR-synthesized images and affects the relationship between the foreground and background of DIBR-synthesized images. Thus, we can accurately evaluate DIBR-synthesized image quality through a joint representation of texture and depth structures. Experiments show that our TDI outperforms the competing state-of-the-art algorithms in predicting the visual quality of DIBR-synthesized images.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Still, it is often impractical to collect a full range of 360-degree viewpoint images. Therefore, it is necessary to synthesize virtual viewpoint images from existing reference viewpoint images by relying on virtual viewpoint synthesis techniques (Wang et al, 2020 , 2021 ; Li et al, 2021a ; Ling et al, 2021 ).…”

Section: Introductionmentioning

confidence: 99%

DIBR-Synthesized Image Quality Assessment With Texture and Depth Information

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…The PCC measures the estimation accuracy. In addition, the outputs of the PM 2.5 concentration measurement models need to be non-linearly mapped by a logistic function before calculating the PCC value [20,33,34]. The SCC and KCC measure the estimation monotonicity.…”

Section: Testing Datasetmentioning

confidence: 99%

PM2.5 Concentration Measurement Based on Image Perception

2022

Self Cite

View full text Add to dashboard Cite

PM2.5 in the atmosphere causes severe air pollution and dramatically affects the normal production and lives of residents. The real-time monitoring of PM2.5 concentrations has important practical significance for the construction of ecological civilization. The mainstream PM2.5 concentration prediction algorithms based on electrochemical sensors have some disadvantages, such as high economic cost, high labor cost, time delay, and more. To this end, we propose a simple and effective PM2.5 concentration prediction algorithm based on image perception. Specifically, the proposed method develops a natural scene statistical prior to estimating the saturation loss caused by the ’haze’ formed by PM2.5. After extracting the prior features, this paper uses the feedforward neural network to achieve the mapping function from the proposed prior features to the PM2.5 concentration values. Experiments constructed on the public Air Quality Image Dataset (AQID) show the superiority of our proposed PM2.5 concentration measurement method compared to state-of-the-art related PM2.5 concentration monitoring methods.

show abstract

“…Computer vision has been widely used in intelligent transportation fields [1][2][3][4][5][6][7][8] such as accurate identification of persons [9][10][11], reasonable allocation of traffic resources, and improvement of large-scale traffic linkage scheduling. Vehicle detection, as one of the important branches, provides basic support for the subsequent high-level tasks of vehicle decision planning and behavior control.…”

Section: Introductionmentioning

confidence: 99%

Part-Aware Refinement Network for Occlusion Vehicle Detection

Wang

Huang

et al. 2022

Electronics

Self Cite

View full text Add to dashboard Cite

Traditional machine learning approaches are susceptible to factors such as object scale, occlusion, leading to low detection efficiency and poor versatility in vehicle detection applications. To tackle this issue, we propose a part-aware refinement network, which combines multi-scale training and component confidence generation strategies in vehicle detection. Specifically, we divide the original single-valued prediction confidence and adopt the confidence of the visible part of the vehicle to correct the absolute detection confidence of the vehicle. That reduces the impact of occlusion on the detection effect. Simultaneously, we relabel the KITTI data, adding the detailed occlusion information of the vehicles. Then, the deep neural network model is trained and tested using the new images. Our proposed method can automatically extract the vehicle features and solve larger error problems when locating vehicles in traditional approaches. Extensive experimental results on KITTI datasets show that our method significantly outperforms the state-of-the-arts while maintaining the detection time.

show abstract

Reference-Free DIBR-Synthesized Video Quality Metric in Spatial and Temporal Domains

Cited by 22 publications

References 62 publications

DIBR-Synthesized Image Quality Assessment With Texture and Depth Information

DIBR-Synthesized Image Quality Assessment With Texture and Depth Information

PM2.5 Concentration Measurement Based on Image Perception

Part-Aware Refinement Network for Occlusion Vehicle Detection

Contact Info

Product

Resources

About