English

Upright adjustment with graph convolutional networks

Computer Vision and Pattern Recognition 2024-06-04 v1

Abstract

We present a novel method for the upright adjustment of 360 images. Our network consists of two modules, which are a convolutional neural network (CNN) and a graph convolutional network (GCN). The input 360 images is processed with the CNN for visual feature extraction, and the extracted feature map is converted into a graph that finds a spherical representation of the input. We also introduce a novel loss function to address the issue of discrete probability distributions defined on the surface of a sphere. Experimental results demonstrate that our method outperforms fully connected based methods.

Keywords

Cite

@article{arxiv.2406.00263,
  title  = {Upright adjustment with graph convolutional networks},
  author = {Raehyuk Jung and Sungmin Cho and Junseok Kwon},
  journal= {arXiv preprint arXiv:2406.00263},
  year   = {2024}
}

Comments

ICIP 2020

R2 v1 2026-06-28T16:49:17.895Z