PanoFormer: Panorama Transformer for Indoor 360 Depth Estimation. (arXiv:2203.09283v2 [cs.CV] UPDATED)

Existing panoramic depth estimation methods based on convolutional neural
networks (CNNs) focus on removing panoramic distortions, failing to perceive
panoramic structures efficiently due to the fixed receptive field in CNNs. This
paper proposes the panorama transformer (named PanoFormer) to estimate the
depth in panorama images, with tangent patches from spherical domain, learnable
token flows, and panorama specific metrics. In particular, we divide patches on
the spherical tangent domain into tokens to reduce the negative effect of
panoramic distortions. Since the …

arxiv cv panorama transformer