A spherical input resampling trick transfers planar pretrained backbone weights to 360-degree segmentation, with a channel-attention branch adding moderate gains.
Omnidirectional stereo depth estimation based on spherical deep network,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
360-Degree Full-view Image Segmentation by Spherical Convolution compatible with Large-scale Planar Pre-trained Models
A spherical input resampling trick transfers planar pretrained backbone weights to 360-degree segmentation, with a channel-attention branch adding moderate gains.