SGFormer: Spherical Geometry Transformer for 360 Depth Estimation

arXiv:2404.14979v1 Announce Type: new
Abstract: Panoramic distortion poses a significant challenge in 360 depth estimation, particularly pronounced at the north and south poles. Existing methods either adopt a bi-projection fusion strategy to remove distortions or model long-range dependencies to capture global structures, which can result in either unclear structure or insufficient local perception. In this paper, we propose a spherical geometry transformer, named SGFormer, to address the above issues, with an innovative step to integrate spherical geometric priors into vision …

abstract arxiv challenge cs.ai cs.cv dependencies fusion geometry global projection strategy transformer type