2019 IEEE International Conference on Image Processing (ICIP) 2019
DOI: 10.1109/icip.2019.8803578
|View full text |Cite
|
Sign up to set email alerts
|

Graph-Based Detection of Seams In 360-Degree Images

Abstract: In this paper, we propose an algorithm to detect a specific kind of distortions, referred to as seams, which commonly occur when a 360-degree image is represented in planar domain by projecting the sphere to a polyhedron, e.g, via the Cube Map (CM) projection, and undergoes lossy compression. The proposed algorithm exploits a graph-based representation to account for the actual sampling density of the 360-degree signal in the native spherical domain. The CM image is considered as a signal lying on a graph defi… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2020
2020
2020
2020

Publication Types

Select...
2

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(1 citation statement)
references
References 22 publications
0
1
0
Order By: Relevance
“…(It is expected that such a behavior is even more pronounced when the ERP format is used in the planar domain, which has more re-sampling and geometrical distortion than EAC. ); (iv) the uniform sampling with 40-degree fieldof-view provides the best performance for most of the metrics; (v) none of the metrics performs good enough on seams, which is a highly localized distortion that can be hidden on the global metrics; this result highlights the need for specific artifact metrics, such as [6]; and (vi) finally, it is possible to notice that the performance of the different metrics varies significantly according to the different distortion types and that there is not a single metric that performs the best for each individual distortion.…”
Section: Resultsmentioning
confidence: 99%
“…(It is expected that such a behavior is even more pronounced when the ERP format is used in the planar domain, which has more re-sampling and geometrical distortion than EAC. ); (iv) the uniform sampling with 40-degree fieldof-view provides the best performance for most of the metrics; (v) none of the metrics performs good enough on seams, which is a highly localized distortion that can be hidden on the global metrics; this result highlights the need for specific artifact metrics, such as [6]; and (vi) finally, it is possible to notice that the performance of the different metrics varies significantly according to the different distortion types and that there is not a single metric that performs the best for each individual distortion.…”
Section: Resultsmentioning
confidence: 99%