Inter-view consistent hole filling in view extrapolation for multi-view image generation

Yoon, Soo Sung; Sohn, Hosik; Jung, Yong Ju; Ro, Yong Man

doi:10.1109/icip.2014.7025583

Cited by 19 publications

(42 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Inter-view consistency [19] Exemplar-based inpaiting [10] No difference (b) Figure 6. Subjective assessment results for viewing preference.…”

Section: Viewing Preferencementioning

confidence: 98%

“…In this paper, we set ω 1 =0.1and ω 2 =0.9 for the inter-view consistency. The results and detail explanation of this method are referred in [19].…”

Section: ) Multi-view Generationmentioning

confidence: 99%

“…The new cost function is given by Figure 4. Illustration of the "inter-view consistency" method [19]. (a) Current virtual view generated by the 3D warping from a reference view.…”

Section: ) Multi-view Generationmentioning

confidence: 99%

“…Notably, this conventional method cannot guarantee the inter-view consistency between adjacent views, since it only works on view-by-view to fill the holes of each view. 3) The "inter-view consistency" method for the hole filling minimizes LR image mismatch in multi-view generation [19]. An interview consistency term is added to make a new cost function that finds the best candidate patch.…”

Section: ) Multi-view Generationmentioning

confidence: 99%

“…The first two methods are the widely used conventional hole filling methods that do not take into account inter-view consistency between adjacent views: 1) the hole filling method employed in the MPEG VSRS version 3.5 [9] (throughout the paper, we call as "VSRS") and 2) "exemplar based-inpainting" [10]. 3) The other is an enhancement of "exemplar-based inpainting" method [19] that takes into account inter-view consistency for reducing the LR image mismatch between adjacent views. Hereafter, we call it as "inter-view consistency" method.…”

Section: ) Multi-view Generationmentioning

confidence: 99%

See 4 more Smart Citations

Investigating experienced quality factors in synthesized multi-view stereo images

Kim

Jung

Yoon

et al. 2014

2014 19th International Conference on Digital Signal Processing

Self Cite

View full text Add to dashboard Cite

In this study, we investigated the quality factors in view synthesis that might lead to the visual discomfort and degradation of the overall viewing quality of the synthesized multi-view stereo or free viewpoint images. In particular, we focused on the investigation of the left and right (LR) image mismatch that might be one of the most important quality factors in the stereoscopic viewing. In order to measure how severely this factor influences the visual comfort and overall quality, we conducted a series of subjective assessment experiments on the visual comfort and viewing preference. In the subjective experiments, we compared the stereo view synthesis results of three different hole filling methods, because incorrectly filled holes could cause severe mismatches between the left-and rightview images. The subjective results revealed that the LR image mismatch could induce more visual discomfort and lower overall quality of stereoscopic images. Also, the results indicated that the visual comfort and overall quality were able to be improved by considering the inter-view consistency in multi-view stereo generation.

show abstract

“…Inter-view consistency [19] Exemplar-based inpaiting [10] No difference (b) Figure 6. Subjective assessment results for viewing preference.…”

Section: Viewing Preferencementioning

confidence: 98%

“…In this paper, we set ω 1 =0.1and ω 2 =0.9 for the inter-view consistency. The results and detail explanation of this method are referred in [19].…”

Section: ) Multi-view Generationmentioning

confidence: 99%

“…The new cost function is given by Figure 4. Illustration of the "inter-view consistency" method [19]. (a) Current virtual view generated by the 3D warping from a reference view.…”

Section: ) Multi-view Generationmentioning

confidence: 99%

Section: ) Multi-view Generationmentioning

confidence: 99%

Section: ) Multi-view Generationmentioning

confidence: 99%

See 3 more Smart Citations