Measurement of critical temporal inconsistency for quality assessment of synthesized video

Kim, Hak Gu; Ro, Yong Man

doi:10.1109/icip.2016.7532513

Cited by 11 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generally, a better metric produces higher PLCC and SRCC values, as well as a lower RMSE value. To validate the advantages of the proposed metric, five DIBR‐synthesised VQA metrics are employed for comparison, including CQM [10 ], PSPTNR [12 ], CTI [9 ], NR_MWT [13 ] and FDI [11 ]. Furthermore, six representative DIBR‐synthesised IQA metrics are also compared, including Bosc [3 ], 3DSwIM [4 ], MW‐PSNR [5 ], MP‐PSNR [6 ], NIQSV+ [7 ] and APT [8 ].…”

Section: Resultsmentioning

confidence: 99%

“…Although numerous efforts have been made in image quality assessment (IQA) for view synthesis in the past decade [3–8 ], they are limited in handling synthesised videos. The underlying reason is that they only quantify the spatial distortions, but are helpless facing the most annoying temporal distortions in the DIBR‐synthesised videos [9 ]. Further, the existing video quality assessment (VQA) models are mainly devised for measuring global distortion and thus have difficulty in capturing the local geometric distortion in synthesised videos.…”

Section: Introductionmentioning

confidence: 99%

“…In [10 ], Sun and co‐authors proposed a colour quality metric (CQM) for DIBR‐based videos by measuring the contrast, luminance and boundary distortions, respectively. Kim and Ro [9 ] first leveraged optical‐flow to detect flickering regions, and the structural similarity on the flickering regions was calculated. Then, a threshold was used to select the most important errors.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

DIBR‐synthesised video quality assessment by measuring geometric distortion and spatiotemporal inconsistency

Huang

Zhou

et al. 2020

Electron. lett.

View full text Add to dashboard Cite

Depth‐image‐based rendering (DIBR), as the most popular view synthesis method, is commonly used in the application of multi‐view and free‐viewpoint videos. However, the quality evaluation of DIBR‐synthesised videos remains largely unexplored, which may hinder the development of more advanced view synthesis technology. With this motivation, this Letter presents a new quality metric for DIBR‐synthesised videos. Specifically, the disoccluded regions are first detected based on an adaptive threshold to quantify geometric distortions. An energy‐based sequence mapping strategy is proposed to portray spatiotemporal inconsistency by calculating first‐order and second‐order similarities in the gradient magnitude domain and the Laplace‐of‐Gaussian domain, respectively. Finally, the overall quality score is generated by pooling the scores of geometric distortion and spatiotemporal inconsistency. Experimental results demonstrate that the proposed metric outperforms the state‐of‐the‐art metrics dedicated to DIBR‐synthesised images and videos.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

DIBR‐synthesised video quality assessment by measuring geometric distortion and spatiotemporal inconsistency

Huang

Zhou

et al. 2020

Electron. lett.

View full text Add to dashboard Cite

show abstract

“…In [103], Kim et al also proposed a NR metric (CTI) to measure the temporal inconsistency and flicker regions in the DIBR-synthesized video. First, the flicker regions are detected from the difference between motion-compensated consecutive frames.…”

Section: Nr Metricsmentioning

confidence: 99%