Omnidirectional Video Super-Resolution using Deep Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908411072872448 |
|---|---|
| author | Baniya, Arbind Agrahari Lee, Tsz-Kwan Eklund, Peter W. Aryal, Sunil |
| author_facet | Baniya, Arbind Agrahari Lee, Tsz-Kwan Eklund, Peter W. Aryal, Sunil |
| contents | Omnidirectional Videos (or 360° videos) are widely used in Virtual Reality (VR) to facilitate immersive and interactive viewing experiences. However, the limited spatial resolution in 360° videos does not allow for each degree of view to be represented with adequate pixels, limiting the visual quality offered in the immersive experience. Deep learning Video Super-Resolution (VSR) techniques used for conventional videos could provide a promising software-based solution; however, these techniques do not tackle the distortion present in equirectangular projections of 360° video signals. An additional obstacle is the limited availability of 360° video datasets for study. To address these issues, this paper creates a novel 360° Video Dataset (360VDS) with a study of the extensibility of conventional VSR models to 360° videos. This paper further proposes a novel deep learning model for 360° Video Super-Resolution (360° VSR), called Spherical Signal Super-resolution with a Proportioned Optimisation (S3PO). S3PO adopts recurrent modelling with an attention mechanism, unbound from conventional VSR techniques like alignment. With a purpose-built feature extractor and a novel loss function addressing spherical distortion, S3PO outperforms most state-of-the-art conventional VSR models and 360°~specific super-resolution models on 360° video datasets. A step-wise ablation study is presented to understand and demonstrate the impact of the chosen architectural sub-components, targeted training and optimisation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_14803 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Omnidirectional Video Super-Resolution using Deep Learning Baniya, Arbind Agrahari Lee, Tsz-Kwan Eklund, Peter W. Aryal, Sunil Multimedia Computer Vision and Pattern Recognition Machine Learning Omnidirectional Videos (or 360° videos) are widely used in Virtual Reality (VR) to facilitate immersive and interactive viewing experiences. However, the limited spatial resolution in 360° videos does not allow for each degree of view to be represented with adequate pixels, limiting the visual quality offered in the immersive experience. Deep learning Video Super-Resolution (VSR) techniques used for conventional videos could provide a promising software-based solution; however, these techniques do not tackle the distortion present in equirectangular projections of 360° video signals. An additional obstacle is the limited availability of 360° video datasets for study. To address these issues, this paper creates a novel 360° Video Dataset (360VDS) with a study of the extensibility of conventional VSR models to 360° videos. This paper further proposes a novel deep learning model for 360° Video Super-Resolution (360° VSR), called Spherical Signal Super-resolution with a Proportioned Optimisation (S3PO). S3PO adopts recurrent modelling with an attention mechanism, unbound from conventional VSR techniques like alignment. With a purpose-built feature extractor and a novel loss function addressing spherical distortion, S3PO outperforms most state-of-the-art conventional VSR models and 360°~specific super-resolution models on 360° video datasets. A step-wise ablation study is presented to understand and demonstrate the impact of the chosen architectural sub-components, targeted training and optimisation. |
| title | Omnidirectional Video Super-Resolution using Deep Learning |
| topic | Multimedia Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2506.14803 |