Upright Adjustment with Graph Convolutional Networks
- Authors
- Jung, R.; Cho, S.; Kwon, Junseok
- Issue Date
- Oct-2020
- Publisher
- IEEE Computer Society
- Keywords
- Graph convolution; Upright adjustment
- Citation
- Proceedings - International Conference on Image Processing, ICIP, v.2020-October, pp 1058 - 1062
- Pages
- 5
- Journal Title
- Proceedings - International Conference on Image Processing, ICIP
- Volume
- 2020-October
- Start Page
- 1058
- End Page
- 1062
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/44021
- DOI
- 10.1109/ICIP40778.2020.9190715
- ISSN
- 1522-4880
- 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. © 2020 IEEE.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Software > School of Computer Science and Engineering > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/44021)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.