Graph-Based Detection of Seams In 360-Degree Images

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 defined on the spherical surface. The spectra of the processed and the original signals, computed by applying the Graph Fourier Transform, are compared to detect the seams. To test our method a dataset of compressed CM 360-degree images, annotated by experts, has been created. The performance of the proposed algorithm is compared to those achieved by baseline metrics, as well as to the same approach based on spectral comparison but ignoring the spherical nature of the signal. The experimental results show that the proposed method has the best performance and can successfully detect up to approximately 90% of visible seams on our dataset.