Upright adjustment with graph convolutional networks
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913373478715392 |
|---|---|
| author | Jung, Raehyuk Cho, Sungmin Kwon, Junseok |
| author_facet | Jung, Raehyuk Cho, Sungmin Kwon, Junseok |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_00263 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Upright adjustment with graph convolutional networks Jung, Raehyuk Cho, Sungmin Kwon, Junseok Computer Vision and Pattern Recognition 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. |
| title | Upright adjustment with graph convolutional networks |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.00263 |